{
"slug": "model-watch-monthly-2026-08",
"series": "monthly",
"series_label": "MONTHLY · MODEL WATCH",
"issue": 1,
"title": "Monthly Model Watch #1",
"language": "en",
"window_start": "2026-08-01T00:00:00+00:00",
"window_end": "2026-09-01T00:00:00+00:00",
"window_text": "Aug 1-31, 2026 UTC",
"cutoff": "2026-09-01T16:00:00+00:00",
"generated_at": "2026-09-04T07:26:21+00:00",
"methodology": "v1.1 (2026-08-10)",
"methodology_hash": "e66c7e8c864a2233",
"source": "monthly_metrics_2026-08.json",
"hit_rule": "direction: exit tp1/tp2 -> hit, sl -> miss, expiry -> sign of gross pnl",
"bibtex_key": "mm_modelwatch_monthly_2026m08",
"research_question": "who led the month, which tickers were readable, who saw the turn first, and does a model agreeing with itself across timeframes/horizons make its call stronger?",
"base_field_hit": {
"n": 19383,
"hit_rate": 0.4633
},
"market_state": {
"panel": "market_state_6p2",
"month": {
"start": "2026-08-01",
"end": "2026-09-01",
"days": 31
},
"prev_month_partial": {
"start": "2026-07-15",
"end": "2026-08-01",
"days": 17,
"partial": true
},
"current": {
"btc_net_pct": 24.95,
"realized_vol_ann_pct": 41.53,
"volume_top5_usd_bn": 65.9696,
"volume_top5_mom_pct": 135.9,
"avg_pairwise_corr": 0.79
},
"previous_partial_month": {
"btc_net_pct": -3.31,
"realized_vol_ann_pct": 27.33,
"volume_top5_usd_bn": 27.9598,
"avg_pairwise_corr": 0.79
},
"snapshot_line": "BTC net +24.95% (prior -3.31%) - ann vol 41.5% (was 27.3%) - TOP5 volume $65.97B, +136% m/m - pairwise corr 0.79 (was 0.79)",
"exchange": "binance",
"audit_filter_applied": true,
"source": "single-exchange (binance) daily candle recompute, market_state_2026-08.json; the prior-month block is the pack's own prev_month_partial (Jul 15-31)",
"audit_note": "Market-state row is computed on a single-exchange (binance) daily candle series, as in the weekly series after the audit that found the raw table mixes two exchanges. The prior-month block is PARTIAL: audited daily candles start 2026-07-15, so it covers 17 days (Jul 15-31), and the TOP5 volume figure compares a 31-day sum with a 17-day sum -- a level difference, not a like-for-like change.",
"weeks": {
"W1": {
"btc_net_pct": 2.09,
"realized_vol_ann_pct": 11.42,
"regime": "calm"
},
"W2": {
"btc_net_pct": -3.08,
"realized_vol_ann_pct": 10.03,
"regime": "calm"
},
"W3": {
"btc_net_pct": 23.58,
"realized_vol_ann_pct": 65.02,
"regime": "volatile"
},
"W4": {
"btc_net_pct": -0.07,
"realized_vol_ann_pct": 30.85,
"regime": "volatile"
}
},
"volatility_rule": "volatile if realized_vol_ann_pct >= median(W1..W4) else calm",
"median_realized_vol_ann_pct": 21.14,
"delta_month_vs_prev_partial": {
"btc_net_pct": 28.26,
"realized_vol_ann_pct": 14.2,
"avg_daily_range_pct": 0.38,
"volume_top5_usd_pct": 135.9,
"avg_pairwise_corr": 0.0,
"note": "August (31 days) vs 15-31 July (17 days, PARTIAL -- daily candles start 2026-07-15); volume is a sum, so volume_top5_usd_pct compares a 31-day sum with a 17-day sum and is NOT a like-for-like change"
},
"controls": {
"w4_matches_published": {
"pins_source": "market_state_2026-08-24.json -> 'current' (the published wave-4 week)",
"block": "W4",
"published": {
"btc_net_pct": -0.07,
"realized_vol_ann_pct": 30.85,
"volume_top5_usd_bn": 19.7224,
"avg_pairwise_corr": 0.85
},
"got": {
"btc_net_pct": -0.07,
"realized_vol_ann_pct": 30.85,
"volume_top5_usd_bn": 19.7224,
"avg_pairwise_corr": 0.85
},
"match": {
"btc_net_pct": true,
"realized_vol_ann_pct": true,
"volume_top5_usd_bn": true,
"avg_pairwise_corr": true
},
"tolerance": {
"btc_net_pct": 0.05,
"realized_vol_ann_pct": 0.5,
"volume_top5_usd_bn": 0.05,
"avg_pairwise_corr": 0.02
},
"all_match": true
},
"w3_matches_published_previous": {
"pins_source": "market_state_2026-08-24.json -> 'previous' (the wave-4 run's prev week)",
"block": "W3",
"published": {
"btc_net_pct": 23.58,
"realized_vol_ann_pct": 65.02,
"volume_top5_usd_bn": 25.9715,
"avg_pairwise_corr": 0.81
},
"got": {
"btc_net_pct": 23.58,
"realized_vol_ann_pct": 65.02,
"volume_top5_usd_bn": 25.9715,
"avg_pairwise_corr": 0.81
},
"match": {
"btc_net_pct": true,
"realized_vol_ann_pct": true,
"volume_top5_usd_bn": true,
"avg_pairwise_corr": true
},
"tolerance": {
"btc_net_pct": 0.05,
"realized_vol_ann_pct": 0.5,
"volume_top5_usd_bn": 0.05,
"avg_pairwise_corr": 0.02
},
"all_match": true
},
"note": "W4 and W3 of this run are exactly the two weeks the wave-4 market panel computed, with the same audit filter, so both must reproduce. Non-fatal: a MISMATCH means the exchange filter or the symbol set moved -- send the log, do not publish the row."
},
"regime_days": {
"2026-08-01": {
"move_pct": -0.13,
"regime": "flat"
},
"2026-08-02": {
"move_pct": 0.81,
"regime": "flat"
},
"2026-08-03": {
"move_pct": 0.09,
"regime": "flat"
},
"2026-08-04": {
"move_pct": 0.93,
"regime": "flat"
},
"2026-08-05": {
"move_pct": 0.98,
"regime": "flat"
},
"2026-08-06": {
"move_pct": -0.57,
"regime": "flat"
},
"2026-08-07": {
"move_pct": 0.88,
"regime": "flat"
},
"2026-08-08": {
"move_pct": 0.16,
"regime": "flat"
},
"2026-08-09": {
"move_pct": 0.09,
"regime": "flat"
},
"2026-08-10": {
"move_pct": -1.63,
"regime": "trend"
},
"2026-08-11": {
"move_pct": -0.56,
"regime": "flat"
},
"2026-08-12": {
"move_pct": -0.02,
"regime": "flat"
},
"2026-08-13": {
"move_pct": -0.25,
"regime": "flat"
},
"2026-08-14": {
"move_pct": -0.67,
"regime": "flat"
},
"2026-08-15": {
"move_pct": 0.07,
"regime": "flat"
},
"2026-08-16": {
"move_pct": -0.35,
"regime": "flat"
},
"2026-08-17": {
"move_pct": 2.55,
"regime": "trend"
},
"2026-08-18": {
"move_pct": 0.21,
"regime": "flat"
},
"2026-08-19": {
"move_pct": 7.82,
"regime": "trend"
},
"2026-08-20": {
"move_pct": 5.07,
"regime": "trend"
},
"2026-08-21": {
"move_pct": 7.26,
"regime": "trend"
},
"2026-08-22": {
"move_pct": -1.67,
"regime": "trend"
},
"2026-08-23": {
"move_pct": 0.69,
"regime": "flat"
},
"2026-08-24": {
"move_pct": 1.61,
"regime": "trend"
},
"2026-08-25": {
"move_pct": -0.58,
"regime": "flat"
},
"2026-08-26": {
"move_pct": 0.63,
"regime": "flat"
},
"2026-08-27": {
"move_pct": 1.53,
"regime": "trend"
},
"2026-08-28": {
"move_pct": -2.91,
"regime": "trend"
},
"2026-08-29": {
"move_pct": 0.48,
"regime": "flat"
},
"2026-08-30": {
"move_pct": -0.7,
"regime": "flat"
},
"2026-08-31": {
"move_pct": 1.19,
"regime": "flat"
}
},
"alive_slice_context": {
"abs_move_1d_pct": {
"A": 1.536,
"B": 1.979
},
"btc_realized_vol_ann_pct_hourly": {
"A": 33.46,
"B": 36.92
}
}
},
"key_finding": {
"label": "KEY FINDING · OBSERVATION (one monthly window)",
"text": "Field accuracy went 45.0% -> 46.3% (+1.4pp) from the partial July to August with 5 of 7 models improving, 3 distinct model lines led the four weeks, and no monthly title was awarded.",
"evidence_level": "observation"
},
"tables": {
"leaderboard": {
"rows": [
{
"model": "claude-opus-5",
"n": 2281,
"hit_rate": 0.4779,
"wilson_95": [
0.4574,
0.4984
],
"coverage": 0.3889,
"model_label": "claude-opus-5",
"insufficient": false
},
{
"model": "gemini-3.1-pro",
"n": 3033,
"hit_rate": 0.4761,
"wilson_95": [
0.4584,
0.4939
],
"coverage": 0.5177,
"model_label": "gemini-3.1-pro",
"insufficient": false
},
{
"model": "claude-fable-5",
"n": 2812,
"hit_rate": 0.4673,
"wilson_95": [
0.4489,
0.4858
],
"coverage": 0.48,
"model_label": "claude-fable-5",
"insufficient": false
},
{
"model": "gpt-5.6-sol",
"n": 2970,
"hit_rate": 0.4586,
"wilson_95": [
0.4407,
0.4765
],
"coverage": 0.5064,
"model_label": "gpt-5.6-sol",
"insufficient": false
},
{
"model": "qwen-3.8-max",
"n": 3001,
"hit_rate": 0.4565,
"wilson_95": [
0.4388,
0.4744
],
"coverage": 0.5166,
"model_label": "qwen-3.8-max (incl. 3.7-era, Aug 1-5)",
"insufficient": false
},
{
"model": "deepseek-v4-pro",
"n": 2578,
"hit_rate": 0.4554,
"wilson_95": [
0.4362,
0.4747
],
"coverage": 0.4397,
"model_label": "deepseek-v4-pro",
"insufficient": false
},
{
"model": "grok-4.6",
"n": 2708,
"hit_rate": 0.4527,
"wilson_95": [
0.4341,
0.4715
],
"coverage": 0.4621,
"model_label": "grok-4.6 (incl. 4.5-era, Aug 1-24)",
"insufficient": false
}
],
"title_awarded": false,
"title_rule": ">=5pp gap AND non-overlapping 95% CI, N>=10",
"top2_gap_pp": 0.2,
"movement_vs_prior_window": [
{
"model": "claude-opus-5",
"hit_rate_prior_window": 0.4492,
"n_prior_window": 3448,
"hit_rate_monthly1": 0.4779,
"delta_pp": 2.9,
"rank_monthly1": 1
},
{
"model": "gemini-3.1-pro",
"hit_rate_prior_window": 0.4511,
"n_prior_window": 2813,
"hit_rate_monthly1": 0.4761,
"delta_pp": 2.5,
"rank_monthly1": 2
},
{
"model": "claude-fable-5",
"hit_rate_prior_window": 0.445,
"n_prior_window": 2690,
"hit_rate_monthly1": 0.4673,
"delta_pp": 2.2,
"rank_monthly1": 3
},
{
"model": "gpt-5.6-sol",
"hit_rate_prior_window": 0.4431,
"n_prior_window": 3085,
"hit_rate_monthly1": 0.4586,
"delta_pp": 1.6,
"rank_monthly1": 4
},
{
"model": "qwen-3.8-max",
"hit_rate_prior_window": 0.4568,
"n_prior_window": 3371,
"hit_rate_monthly1": 0.4565,
"delta_pp": -0.0,
"rank_monthly1": 5
},
{
"model": "deepseek-v4-pro",
"hit_rate_prior_window": 0.4505,
"n_prior_window": 1869,
"hit_rate_monthly1": 0.4554,
"delta_pp": 0.5,
"rank_monthly1": 6
},
{
"model": "grok-4.6",
"hit_rate_prior_window": 0.453,
"n_prior_window": 2265,
"hit_rate_monthly1": 0.4527,
"delta_pp": -0.0,
"rank_monthly1": 7
}
],
"prior_window_note": "prior = month.prior_window.model_watch.leaderboard, the PARTIAL July (forecasts from Jul 11) computed by the pack at the prior cutoff",
"note": "No monthly title is awarded this issue. Title rule: **>=5pp gap AND non-overlapping 95% CI, N>=10** per side. claude-opus-5's lead over gemini-3.1-pro is 0.2pp and their CIs overlap, so neither condition is met."
},
"ticker": {
"rows": [
{
"symbol": "BNB",
"n": 3857,
"hit_rate": 0.4807,
"wilson_95": [
0.4649,
0.4965
],
"prior_hit_rate": 0.4548,
"prior_n": 2720
},
{
"symbol": "SOL",
"n": 3928,
"hit_rate": 0.4733,
"wilson_95": [
0.4577,
0.4889
],
"prior_hit_rate": 0.4325,
"prior_n": 3443
},
{
"symbol": "XRP",
"n": 3835,
"hit_rate": 0.4673,
"wilson_95": [
0.4515,
0.4831
],
"prior_hit_rate": 0.4455,
"prior_n": 3053
},
{
"symbol": "BTC",
"n": 4068,
"hit_rate": 0.4648,
"wilson_95": [
0.4496,
0.4802
],
"prior_hit_rate": 0.4418,
"prior_n": 4169
},
{
"symbol": "ETH",
"n": 3695,
"hit_rate": 0.4287,
"wilson_95": [
0.4128,
0.4447
],
"prior_hit_rate": 0.4781,
"prior_n": 4564
}
],
"best": "BNB",
"hardest": "ETH",
"all_above_51pct": false,
"prior_note": "prior = month.prior_window.model_watch.by_symbol"
},
"pairs_top": [
{
"model": "claude-opus-5",
"symbol": "SOL",
"n": 482,
"hit_rate": 0.5041
},
{
"model": "gemini-3.1-pro",
"symbol": "XRP",
"n": 640,
"hit_rate": 0.4969
},
{
"model": "gemini-3.1-pro",
"symbol": "BNB",
"n": 568,
"hit_rate": 0.4965
},
{
"model": "qwen-3.8-max",
"symbol": "BNB",
"n": 587,
"hit_rate": 0.4957
},
{
"model": "claude-opus-5",
"symbol": "BNB",
"n": 447,
"hit_rate": 0.4855
},
{
"model": "claude-fable-5",
"symbol": "SOL",
"n": 604,
"hit_rate": 0.4851
}
],
"pairs_worst": [
{
"model": "claude-fable-5",
"symbol": "ETH",
"n": 529,
"hit_rate": 0.4405
},
{
"model": "grok-4.6",
"symbol": "ETH",
"n": 512,
"hit_rate": 0.4199
},
{
"model": "gpt-5.6-sol",
"symbol": "ETH",
"n": 574,
"hit_rate": 0.4164
},
{
"model": "deepseek-v4-pro",
"symbol": "ETH",
"n": 522,
"hit_rate": 0.4119
},
{
"model": "qwen-3.8-max",
"symbol": "ETH",
"n": 576,
"hit_rate": 0.4045
}
],
"reversal_events": {
"definition": "4h grid, trend=sign of prior 24h, counter-move >=2.0% (BTC/ETH) sustained 8h; caller: directional hit, FH 4h/1d, slot in [T-12h, T+FH]",
"events": [
{
"symbol": "BTC",
"t": "2026-08-03T08:00:00+00:00",
"new_side": "long",
"move_8h_pct": 2.1,
"n_callers": 9,
"first_caller": {
"model": "qwen-3.8-max",
"slot": "2026-08-02T20:01:00+00:00",
"fh": "4h",
"tf": "1h",
"confidence": 68
},
"caller_models": [
"claude-fable-5",
"claude-opus-5",
"deepseek-v4-pro",
"gemini-3.1-pro",
"gpt-5.6-sol",
"grok-4.6",
"qwen-3.8-max"
]
},
{
"symbol": "BTC",
"t": "2026-08-28T12:00:00+00:00",
"new_side": "short",
"move_8h_pct": -2.49,
"n_callers": 8,
"first_caller": {
"model": "gpt-5.6-sol",
"slot": "2026-08-28T04:01:00+00:00",
"fh": "4h",
"tf": "1h",
"confidence": 62
},
"caller_models": [
"deepseek-v4-pro",
"gpt-5.6-sol",
"grok-4.6",
"qwen-3.8-max"
]
},
{
"symbol": "ETH",
"t": "2026-08-01T20:00:00+00:00",
"new_side": "long",
"move_8h_pct": 2.27,
"n_callers": 0,
"first_caller": null,
"caller_models": []
},
{
"symbol": "ETH",
"t": "2026-08-10T08:00:00+00:00",
"new_side": "short",
"move_8h_pct": -2.65,
"n_callers": 0,
"first_caller": null,
"caller_models": []
},
{
"symbol": "ETH",
"t": "2026-08-22T00:00:00+00:00",
"new_side": "short",
"move_8h_pct": -3.46,
"n_callers": 1,
"first_caller": {
"model": "gemini-3.1-pro",
"slot": "2026-08-22T00:01:00+00:00",
"fh": "4h",
"tf": "1h",
"confidence": 60
},
"caller_models": [
"gemini-3.1-pro"
]
},
{
"symbol": "ETH",
"t": "2026-08-23T08:00:00+00:00",
"new_side": "long",
"move_8h_pct": 2.14,
"n_callers": 17,
"first_caller": {
"model": "claude-fable-5",
"slot": "2026-08-23T00:01:00+00:00",
"fh": "1d",
"tf": "1d",
"confidence": 62
},
"caller_models": [
"claude-fable-5",
"claude-opus-5",
"deepseek-v4-pro",
"gemini-3.1-pro",
"gpt-5.6-sol",
"grok-4.6",
"qwen-3.8-max"
]
},
{
"symbol": "ETH",
"t": "2026-08-26T16:00:00+00:00",
"new_side": "long",
"move_8h_pct": 2.31,
"n_callers": 13,
"first_caller": {
"model": "gpt-5.6-sol",
"slot": "2026-08-27T00:01:00+00:00",
"fh": "1d",
"tf": "4h",
"confidence": 69
},
"caller_models": [
"claude-fable-5",
"claude-opus-5",
"deepseek-v4-pro",
"gemini-3.1-pro",
"gpt-5.6-sol",
"grok-4.6",
"qwen-3.8-max"
]
},
{
"symbol": "ETH",
"t": "2026-08-28T12:00:00+00:00",
"new_side": "short",
"move_8h_pct": -2.8,
"n_callers": 0,
"first_caller": null,
"caller_models": []
},
{
"symbol": "ETH",
"t": "2026-08-30T16:00:00+00:00",
"new_side": "short",
"move_8h_pct": -2.52,
"n_callers": 1,
"first_caller": {
"model": "deepseek-v4-pro",
"slot": "2026-08-30T04:01:00+00:00",
"fh": "4h",
"tf": "4h",
"confidence": 56
},
"caller_models": [
"deepseek-v4-pro"
]
}
],
"scope_v1": "BTC/ETH only",
"status": "ok"
},
"cross_tf": {
"fh_4h_tf_4h_vs_1h": {
"agree": {
"n": 1989,
"hit_rate": 0.456,
"wilson_95": [
0.4342,
0.478
],
"by_regime": {
"trend": {
"n": 749,
"hit_rate": 0.5661
},
"flat": {
"n": 1240,
"hit_rate": 0.3895
}
}
},
"disagree": {
"n": 91,
"hit_rate": 0.3407,
"wilson_95": [
0.2515,
0.4427
],
"by_regime": {
"trend": {
"n": 54,
"hit_rate": 0.3519
},
"flat": {
"n": 37,
"hit_rate": 0.3243
}
}
},
"mixed_pairs": 993,
"base": {
"n": 3086,
"hit_rate": 0.4618
},
"lift_pp": -0.6
},
"fh_1d_tf_1d_vs_4h": {
"agree": {
"n": 380,
"hit_rate": 0.5079,
"wilson_95": [
0.4578,
0.5578
],
"by_regime": {
"trend": {
"n": 193,
"hit_rate": 0.6528
},
"flat": {
"n": 187,
"hit_rate": 0.3583
}
}
},
"disagree": {
"n": 23,
"hit_rate": 0.8696,
"wilson_95": [
0.6787,
0.9546
],
"by_regime": {
"trend": {
"n": 5,
"hit_rate": 0.6
},
"flat": {
"n": 18,
"hit_rate": 0.9444
}
}
},
"mixed_pairs": 136,
"base": {
"n": 539,
"hit_rate": 0.5399
},
"lift_pp": -3.2
}
},
"cross_fh": {
"fh_4h_confirmed_by_1h": {
"agree": {
"n": 1824,
"hit_rate": 0.4534,
"wilson_95": [
0.4307,
0.4763
],
"by_regime": {
"trend": {
"n": 683,
"hit_rate": 0.5564
},
"flat": {
"n": 1141,
"hit_rate": 0.3918
}
}
},
"disagree": {
"n": 122,
"hit_rate": 0.4016,
"wilson_95": [
0.3189,
0.4903
],
"by_regime": {
"trend": {
"n": 63,
"hit_rate": 0.381
},
"flat": {
"n": 59,
"hit_rate": 0.4237
}
}
},
"mixed_pairs": 1137,
"base": {
"n": 3086,
"hit_rate": 0.4618
},
"lift_pp": -0.8
},
"fh_1d_confirmed_by_4h": {
"agree": {
"n": 316,
"hit_rate": 0.4842,
"wilson_95": [
0.4296,
0.5391
],
"by_regime": {
"trend": {
"n": 156,
"hit_rate": 0.6218
},
"flat": {
"n": 160,
"hit_rate": 0.35
}
}
},
"disagree": {
"n": 32,
"hit_rate": 0.8438,
"wilson_95": [
0.6825,
0.9314
],
"by_regime": {
"trend": {
"n": 11,
"hit_rate": 0.8182
},
"flat": {
"n": 21,
"hit_rate": 0.8571
}
}
},
"mixed_pairs": 191,
"base": {
"n": 539,
"hit_rate": 0.5399
},
"lift_pp": -5.6
}
},
"regime_days": {
"2026-08-01": {
"move_pct": -0.13,
"regime": "flat"
},
"2026-08-02": {
"move_pct": 0.81,
"regime": "flat"
},
"2026-08-03": {
"move_pct": 0.09,
"regime": "flat"
},
"2026-08-04": {
"move_pct": 0.93,
"regime": "flat"
},
"2026-08-05": {
"move_pct": 0.98,
"regime": "flat"
},
"2026-08-06": {
"move_pct": -0.57,
"regime": "flat"
},
"2026-08-07": {
"move_pct": 0.88,
"regime": "flat"
},
"2026-08-08": {
"move_pct": 0.16,
"regime": "flat"
},
"2026-08-09": {
"move_pct": 0.09,
"regime": "flat"
},
"2026-08-10": {
"move_pct": -1.63,
"regime": "trend"
},
"2026-08-11": {
"move_pct": -0.56,
"regime": "flat"
},
"2026-08-12": {
"move_pct": -0.02,
"regime": "flat"
},
"2026-08-13": {
"move_pct": -0.25,
"regime": "flat"
},
"2026-08-14": {
"move_pct": -0.67,
"regime": "flat"
},
"2026-08-15": {
"move_pct": 0.07,
"regime": "flat"
},
"2026-08-16": {
"move_pct": -0.35,
"regime": "flat"
},
"2026-08-17": {
"move_pct": 2.55,
"regime": "trend"
},
"2026-08-18": {
"move_pct": 0.21,
"regime": "flat"
},
"2026-08-19": {
"move_pct": 7.82,
"regime": "trend"
},
"2026-08-20": {
"move_pct": 5.07,
"regime": "trend"
},
"2026-08-21": {
"move_pct": 7.26,
"regime": "trend"
},
"2026-08-22": {
"move_pct": -1.67,
"regime": "trend"
},
"2026-08-23": {
"move_pct": 0.69,
"regime": "flat"
},
"2026-08-24": {
"move_pct": 1.61,
"regime": "trend"
},
"2026-08-25": {
"move_pct": -0.58,
"regime": "flat"
},
"2026-08-26": {
"move_pct": 0.63,
"regime": "flat"
},
"2026-08-27": {
"move_pct": 1.53,
"regime": "trend"
},
"2026-08-28": {
"move_pct": -2.91,
"regime": "trend"
},
"2026-08-29": {
"move_pct": 0.48,
"regime": "flat"
},
"2026-08-30": {
"move_pct": -0.7,
"regime": "flat"
},
"2026-08-31": {
"move_pct": 1.19,
"regime": "flat"
}
},
"side_mix": [
{
"model": "claude-fable-5",
"n": 5858,
"long": 0.3564,
"short": 0.1236,
"sideways": 0.52,
"ls_ratio": 2.88
},
{
"model": "claude-opus-5",
"n": 5865,
"long": 0.2921,
"short": 0.0968,
"sideways": 0.6111,
"ls_ratio": 3.02
},
{
"model": "deepseek-v4-pro",
"n": 5863,
"long": 0.2555,
"short": 0.1842,
"sideways": 0.5603,
"ls_ratio": 1.39
},
{
"model": "gemini-3.1-pro",
"n": 5859,
"long": 0.3173,
"short": 0.2004,
"sideways": 0.4823,
"ls_ratio": 1.58
},
{
"model": "gpt-5.6-sol",
"n": 5865,
"long": 0.2781,
"short": 0.2283,
"sideways": 0.4936,
"ls_ratio": 1.22
},
{
"model": "grok-4.6",
"n": 5860,
"long": 0.2396,
"short": 0.2225,
"sideways": 0.5379,
"ls_ratio": 1.08
},
{
"model": "qwen-3.8-max",
"n": 5809,
"long": 0.3217,
"short": 0.1949,
"sideways": 0.4834,
"ls_ratio": 1.65
}
],
"long_short_ratio_field": {
"value": 1.83,
"method": "mean of the per-model long-share / short-share ratios"
},
"consensus_skew": {
"cells_ge5_same_side": 2225,
"n_mature": 13776,
"hit_rate": 0.4534
},
"fail_of_month": {
"model": "gemini-3.1-pro",
"symbol": "XRP",
"side": "long",
"confidence": 85,
"slot": "2026-08-21T16:01:00+00:00",
"fh": "4h",
"tf": "1h",
"exit_reason": "sl",
"pnl_net_usd": -3.1
},
"counters": {
"forecasts_total": 42654,
"ok_in_gate": 40979,
"out_of_gate": 1604,
"out_of_gate_by_fh": {
"1m": 698,
"1w": 906
},
"invalid": 71,
"mature": 40979,
"mature_directional": 19383,
"mature_sideways": 21596,
"pending_next_issue": 0,
"pending_by_fh": {},
"late_closes": 0,
"uptime": [
{
"fh": "1h",
"tf": "1h",
"slots_seen": 741,
"slots_expected": 744
},
{
"fh": "4h",
"tf": "4h",
"slots_seen": 185,
"slots_expected": 186
},
{
"fh": "4h",
"tf": "1h",
"slots_seen": 185,
"slots_expected": 186
},
{
"fh": "1d",
"tf": "1d",
"slots_seen": 31,
"slots_expected": 31
},
{
"fh": "1d",
"tf": "4h",
"slots_seen": 31,
"slots_expected": 31
}
],
"regime_days": {
"2026-08-01": {
"move_pct": -0.13,
"regime": "flat"
},
"2026-08-02": {
"move_pct": 0.81,
"regime": "flat"
},
"2026-08-03": {
"move_pct": 0.09,
"regime": "flat"
},
"2026-08-04": {
"move_pct": 0.93,
"regime": "flat"
},
"2026-08-05": {
"move_pct": 0.98,
"regime": "flat"
},
"2026-08-06": {
"move_pct": -0.57,
"regime": "flat"
},
"2026-08-07": {
"move_pct": 0.88,
"regime": "flat"
},
"2026-08-08": {
"move_pct": 0.16,
"regime": "flat"
},
"2026-08-09": {
"move_pct": 0.09,
"regime": "flat"
},
"2026-08-10": {
"move_pct": -1.63,
"regime": "trend"
},
"2026-08-11": {
"move_pct": -0.56,
"regime": "flat"
},
"2026-08-12": {
"move_pct": -0.02,
"regime": "flat"
},
"2026-08-13": {
"move_pct": -0.25,
"regime": "flat"
},
"2026-08-14": {
"move_pct": -0.67,
"regime": "flat"
},
"2026-08-15": {
"move_pct": 0.07,
"regime": "flat"
},
"2026-08-16": {
"move_pct": -0.35,
"regime": "flat"
},
"2026-08-17": {
"move_pct": 2.55,
"regime": "trend"
},
"2026-08-18": {
"move_pct": 0.21,
"regime": "flat"
},
"2026-08-19": {
"move_pct": 7.82,
"regime": "trend"
},
"2026-08-20": {
"move_pct": 5.07,
"regime": "trend"
},
"2026-08-21": {
"move_pct": 7.26,
"regime": "trend"
},
"2026-08-22": {
"move_pct": -1.67,
"regime": "trend"
},
"2026-08-23": {
"move_pct": 0.69,
"regime": "flat"
},
"2026-08-24": {
"move_pct": 1.61,
"regime": "trend"
},
"2026-08-25": {
"move_pct": -0.58,
"regime": "flat"
},
"2026-08-26": {
"move_pct": 0.63,
"regime": "flat"
},
"2026-08-27": {
"move_pct": 1.53,
"regime": "trend"
},
"2026-08-28": {
"move_pct": -2.91,
"regime": "trend"
},
"2026-08-29": {
"move_pct": 0.48,
"regime": "flat"
},
"2026-08-30": {
"move_pct": -0.7,
"regime": "flat"
},
"2026-08-31": {
"move_pct": 1.19,
"regime": "flat"
}
},
"grok_era": {
"ids_in_window": [
"grok-4.5",
"grok-4.6"
],
"n_grok45": 4520,
"n_grok46": 1570,
"n_grok45_rows": 4520,
"n_grok46_rows": 1570,
"first_grok46_slot": "2026-08-24T10:01:00+00:00",
"last_grok45_slot": "2026-08-24T09:01:00+00:00",
"first_grok45_slot": "2026-08-01T00:01:00+00:00",
"flip_at": "2026-08-24T09:22:00+00:00",
"flip_inside_window": true,
"prev_window": {
"n_grok45_rows": 6608,
"n_grok46_rows": 0
},
"merged_model_id": "grok-4.6",
"merged_label": "grok-4.6 (incl. 4.5-era, Aug 1-24)",
"lineage_ids": [
"grok-4.5",
"grok-4.6"
],
"lineage_source": "benchmarks.config.lineage_ids(head) for each of the 7 heads + MODEL_SUCCESSION[claude-opus-5=('claude-opus-4.8',), grok-4.6=('grok-4.5',), qwen-3.8-max=('qwen-3.7-max',)]",
"lineage_warnings": [],
"rows_remapped_a_plus_b": 11128,
"note": "window MONTH [2026-08-01T00:00:00+00:00, 2026-09-01T00:00:00+00:00): grok-4.5 rows 4520, grok-4.6 rows 1570; flip 2026-08-24T09:22:00+00:00 is inside this window. All per-model aggregates use the lineage splice grok-4.5 -> grok-4.6 (one row, labelled 'grok-4.6 (incl. 4.5-era, Aug 1-24)'). See lineage_era for the same facts across all 7 heads.",
"cells_with_two_grok_rows": 0
},
"lineage_era": {
"window_key": "MONTH",
"heads": [
"claude-fable-5",
"claude-opus-5",
"deepseek-v4-pro",
"gemini-3.1-pro",
"gpt-5.6-sol",
"grok-4.6",
"qwen-3.8-max"
],
"lineage_map": {
"claude-opus-4.8": "claude-opus-5",
"grok-4.5": "grok-4.6",
"qwen-3.7-max": "qwen-3.8-max"
},
"legacy_by_head": {
"claude-fable-5": [],
"claude-opus-5": [
"claude-opus-4.8"
],
"deepseek-v4-pro": [],
"gemini-3.1-pro": [],
"gpt-5.6-sol": [],
"grok-4.6": [
"grok-4.5"
],
"qwen-3.8-max": [
"qwen-3.7-max"
]
},
"lineage_source": "benchmarks.config.lineage_ids(head) for each of the 7 heads + MODEL_SUCCESSION[claude-opus-5=('claude-opus-4.8',), grok-4.6=('grok-4.5',), qwen-3.8-max=('qwen-3.7-max',)]",
"lineage_resolved_heads": [
"claude-fable-5",
"claude-opus-5",
"deepseek-v4-pro",
"gemini-3.1-pro",
"gpt-5.6-sol",
"grok-4.6",
"qwen-3.8-max"
],
"lineage_warnings": [],
"per_head": {
"claude-fable-5": {
"legacy_ids": [],
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"n_rows_remapped_prev_window": {},
"by_legacy_id": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-01T00:01:00+00:00",
"last_successor_slot": "2026-08-31T23:01:00+00:00",
"n_rows_successor": 6095,
"spliced_in_window": false,
"label": "claude-fable-5"
},
"claude-opus-5": {
"legacy_ids": [
"claude-opus-4.8"
],
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {
"claude-opus-4.8": 0
},
"n_rows_remapped_prev_window": {
"claude-opus-4.8": 6315
},
"by_legacy_id": {
"claude-opus-4.8": {
"n_rows_remapped": {
"MONTH": 0,
"prev_window": 6315
},
"first_slot": null,
"last_slot": null,
"first_slot_prev_window": "2026-07-15T18:01:00+00:00",
"last_slot_prev_window": "2026-07-30T08:01:00+00:00"
}
},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-01T00:01:00+00:00",
"last_successor_slot": "2026-08-31T23:01:00+00:00",
"n_rows_successor": 6095,
"spliced_in_window": false,
"label": "claude-opus-5"
},
"deepseek-v4-pro": {
"legacy_ids": [],
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"n_rows_remapped_prev_window": {},
"by_legacy_id": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-01T00:01:00+00:00",
"last_successor_slot": "2026-08-31T23:01:00+00:00",
"n_rows_successor": 6095,
"spliced_in_window": false,
"label": "deepseek-v4-pro"
},
"gemini-3.1-pro": {
"legacy_ids": [],
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"n_rows_remapped_prev_window": {},
"by_legacy_id": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-01T00:01:00+00:00",
"last_successor_slot": "2026-08-31T23:01:00+00:00",
"n_rows_successor": 6094,
"spliced_in_window": false,
"label": "gemini-3.1-pro"
},
"gpt-5.6-sol": {
"legacy_ids": [],
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"n_rows_remapped_prev_window": {},
"by_legacy_id": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-01T00:01:00+00:00",
"last_successor_slot": "2026-08-31T23:01:00+00:00",
"n_rows_successor": 6095,
"spliced_in_window": false,
"label": "gpt-5.6-sol"
},
"grok-4.6": {
"legacy_ids": [
"grok-4.5"
],
"legacy_ids_seen_in_window": [
"grok-4.5"
],
"n_rows_remapped": {
"grok-4.5": 4520
},
"n_rows_remapped_prev_window": {
"grok-4.5": 6608
},
"by_legacy_id": {
"grok-4.5": {
"n_rows_remapped": {
"MONTH": 4520,
"prev_window": 6608
},
"first_slot": "2026-08-01T00:01:00+00:00",
"last_slot": "2026-08-24T09:01:00+00:00",
"first_slot_prev_window": "2026-07-15T18:01:00+00:00",
"last_slot_prev_window": "2026-07-31T23:01:00+00:00"
}
},
"first_legacy_slot": "2026-08-01T00:01:00+00:00",
"last_legacy_slot": "2026-08-24T09:01:00+00:00",
"first_successor_slot": "2026-08-24T10:01:00+00:00",
"last_successor_slot": "2026-08-31T23:01:00+00:00",
"n_rows_successor": 1570,
"spliced_in_window": true,
"label": "grok-4.6 (incl. 4.5-era, Aug 1-24)"
},
"qwen-3.8-max": {
"legacy_ids": [
"qwen-3.7-max"
],
"legacy_ids_seen_in_window": [
"qwen-3.7-max"
],
"n_rows_remapped": {
"qwen-3.7-max": 870
},
"n_rows_remapped_prev_window": {
"qwen-3.7-max": 6609
},
"by_legacy_id": {
"qwen-3.7-max": {
"n_rows_remapped": {
"MONTH": 870,
"prev_window": 6609
},
"first_slot": "2026-08-01T00:01:00+00:00",
"last_slot": "2026-08-05T09:01:00+00:00",
"first_slot_prev_window": "2026-07-15T18:01:00+00:00",
"last_slot_prev_window": "2026-07-31T23:01:00+00:00"
}
},
"first_legacy_slot": "2026-08-01T00:01:00+00:00",
"last_legacy_slot": "2026-08-05T09:01:00+00:00",
"first_successor_slot": "2026-08-05T10:01:00+00:00",
"last_successor_slot": "2026-08-31T23:01:00+00:00",
"n_rows_successor": 5220,
"spliced_in_window": true,
"label": "qwen-3.8-max (incl. 3.7-era, Aug 1-5)"
}
},
"labels": {
"claude-fable-5": "claude-fable-5",
"claude-opus-5": "claude-opus-5",
"deepseek-v4-pro": "deepseek-v4-pro",
"gemini-3.1-pro": "gemini-3.1-pro",
"gpt-5.6-sol": "gpt-5.6-sol",
"grok-4.6": "grok-4.6 (incl. 4.5-era, Aug 1-24)",
"qwen-3.8-max": "qwen-3.8-max (incl. 3.7-era, Aug 1-5)"
},
"rows_remapped_window": 5390,
"rows_remapped_prev_window": 19532,
"note": "Only the 7 current models are tracked; earlier versions are folded into their successors' lineage. Every per-model aggregate in this pack sees the merged head id; the raw id survives in model_raw. Labels and era spans are generated from the pulled rows, not hardcoded.",
"cells_with_two_rows_per_head": {
"claude-fable-5": 0,
"claude-opus-5": 0,
"deepseek-v4-pro": 0,
"gemini-3.1-pro": 0,
"gpt-5.6-sol": 0,
"grok-4.6": 0,
"qwen-3.8-max": 0
}
},
"series_density": {
"1d": {
"days_with_slots": 31,
"expected_days": 31,
"full_daily_coverage": true,
"in_fh_gate": true,
"n_slots": 31,
"n_rows": 2170,
"days": [
"2026-08-01",
"2026-08-02",
"2026-08-03",
"2026-08-04",
"2026-08-05",
"2026-08-06",
"2026-08-07",
"2026-08-08",
"2026-08-09",
"2026-08-10",
"2026-08-11",
"2026-08-12",
"2026-08-13",
"2026-08-14",
"2026-08-15",
"2026-08-16",
"2026-08-17",
"2026-08-18",
"2026-08-19",
"2026-08-20",
"2026-08-21",
"2026-08-22",
"2026-08-23",
"2026-08-24",
"2026-08-25",
"2026-08-26",
"2026-08-27",
"2026-08-28",
"2026-08-29",
"2026-08-30",
"2026-08-31"
],
"missing_days": []
},
"1h": {
"days_with_slots": 31,
"expected_days": 31,
"full_daily_coverage": true,
"in_fh_gate": true,
"n_slots": 741,
"n_rows": 25935,
"days": [
"2026-08-01",
"2026-08-02",
"2026-08-03",
"2026-08-04",
"2026-08-05",
"2026-08-06",
"2026-08-07",
"2026-08-08",
"2026-08-09",
"2026-08-10",
"2026-08-11",
"2026-08-12",
"2026-08-13",
"2026-08-14",
"2026-08-15",
"2026-08-16",
"2026-08-17",
"2026-08-18",
"2026-08-19",
"2026-08-20",
"2026-08-21",
"2026-08-22",
"2026-08-23",
"2026-08-24",
"2026-08-25",
"2026-08-26",
"2026-08-27",
"2026-08-28",
"2026-08-29",
"2026-08-30",
"2026-08-31"
],
"missing_days": []
},
"1m": {
"days_with_slots": 10,
"expected_days": 31,
"full_daily_coverage": false,
"in_fh_gate": false,
"n_slots": 10,
"n_rows": 700,
"days": [
"2026-08-01",
"2026-08-23",
"2026-08-24",
"2026-08-25",
"2026-08-26",
"2026-08-27",
"2026-08-28",
"2026-08-29",
"2026-08-30",
"2026-08-31"
],
"missing_days": [
"2026-08-02",
"2026-08-03",
"2026-08-04",
"2026-08-05",
"2026-08-06",
"2026-08-07",
"2026-08-08",
"2026-08-09",
"2026-08-10",
"2026-08-11",
"2026-08-12",
"2026-08-13",
"2026-08-14",
"2026-08-15",
"2026-08-16",
"2026-08-17",
"2026-08-18",
"2026-08-19",
"2026-08-20",
"2026-08-21",
"2026-08-22"
]
},
"1w": {
"days_with_slots": 13,
"expected_days": 31,
"full_daily_coverage": false,
"in_fh_gate": false,
"n_slots": 13,
"n_rows": 910,
"days": [
"2026-08-03",
"2026-08-10",
"2026-08-17",
"2026-08-22",
"2026-08-23",
"2026-08-24",
"2026-08-25",
"2026-08-26",
"2026-08-27",
"2026-08-28",
"2026-08-29",
"2026-08-30",
"2026-08-31"
],
"missing_days": [
"2026-08-01",
"2026-08-02",
"2026-08-04",
"2026-08-05",
"2026-08-06",
"2026-08-07",
"2026-08-08",
"2026-08-09",
"2026-08-11",
"2026-08-12",
"2026-08-13",
"2026-08-14",
"2026-08-15",
"2026-08-16",
"2026-08-18",
"2026-08-19",
"2026-08-20",
"2026-08-21"
]
},
"4h": {
"days_with_slots": 31,
"expected_days": 31,
"full_daily_coverage": true,
"in_fh_gate": true,
"n_slots": 185,
"n_rows": 12939,
"days": [
"2026-08-01",
"2026-08-02",
"2026-08-03",
"2026-08-04",
"2026-08-05",
"2026-08-06",
"2026-08-07",
"2026-08-08",
"2026-08-09",
"2026-08-10",
"2026-08-11",
"2026-08-12",
"2026-08-13",
"2026-08-14",
"2026-08-15",
"2026-08-16",
"2026-08-17",
"2026-08-18",
"2026-08-19",
"2026-08-20",
"2026-08-21",
"2026-08-22",
"2026-08-23",
"2026-08-24",
"2026-08-25",
"2026-08-26",
"2026-08-27",
"2026-08-28",
"2026-08-29",
"2026-08-30",
"2026-08-31"
],
"missing_days": []
}
},
"model_roster": {
"current": [
"claude-fable-5",
"claude-opus-5",
"deepseek-v4-pro",
"gemini-3.1-pro",
"gpt-5.6-sol",
"grok-4.6",
"qwen-3.8-max"
],
"current_count": 7,
"current_raw_ids_in_window": [
"claude-fable-5",
"claude-opus-5",
"deepseek-v4-pro",
"gemini-3.1-pro",
"gpt-5.6-sol",
"grok-4.5",
"grok-4.6",
"qwen-3.7-max",
"qwen-3.8-max"
],
"archived_legacy": [
"grok-4.5",
"qwen-3.7-max",
"claude-opus-4.8"
],
"archived_legacy_count": 3,
"archived_legacy_detail": [
{
"model": "grok-4.5",
"n_rows_since": 11128,
"first_slot": "2026-07-15T18:01:00+00:00",
"last_slot": "2026-08-24T09:01:00+00:00"
},
{
"model": "qwen-3.7-max",
"n_rows_since": 7479,
"first_slot": "2026-07-15T18:01:00+00:00",
"last_slot": "2026-08-05T09:01:00+00:00"
},
{
"model": "claude-opus-4.8",
"n_rows_since": 6315,
"first_slot": "2026-07-15T18:01:00+00:00",
"last_slot": "2026-07-30T08:01:00+00:00"
}
],
"archived_excluding_lineage_merged": [],
"tracked_total": 10,
"canon_expected": {
"current": 7,
"archived_legacy": 4,
"tracked_total": 11
},
"matches_canon_11_7_4": false,
"roster_rule_w213": "7 models tracked (current line-up; earlier versions folded into their successors' lineage)",
"canon_expected_w213": {
"current": 7
},
"heads_w213": [
"claude-fable-5",
"claude-opus-5",
"deepseek-v4-pro",
"gemini-3.1-pro",
"gpt-5.6-sol",
"grok-4.6",
"qwen-3.8-max"
],
"matches_canon_7_current": true,
"heads_missing_in_window": [],
"heads_unexpected_in_window": [],
"roster_since": "2026-07-11T00:00:00+00:00",
"note": "current = merged-lineage model ids emitting inside the window (legacy ids are spliced into their successor); archived legacy = raw ids seen since 2026-07-11 that no longer emit in the window. Models retired before 2026-07-11 are not visible to this query. The canon checks are DESCRIPTIVE: if the data says otherwise, the data wins and is printed."
}
},
"uptime": [
{
"fh": "1h",
"tf": "1h",
"slots_seen": 741,
"slots_expected": 744
},
{
"fh": "4h",
"tf": "4h",
"slots_seen": 185,
"slots_expected": 186
},
{
"fh": "4h",
"tf": "1h",
"slots_seen": 185,
"slots_expected": 186
},
{
"fh": "1d",
"tf": "1d",
"slots_seen": 31,
"slots_expected": 31
},
{
"fh": "1d",
"tf": "4h",
"slots_seen": 31,
"slots_expected": 31
}
],
"ok_rate_by_model": {
"claude-opus-5": 1.0,
"claude-fable-5": 0.9989,
"grok-4.6": 1.0,
"qwen-3.8-max": 0.9906,
"deepseek-v4-pro": 0.9997,
"gemini-3.1-pro": 0.9992,
"gpt-5.6-sol": 1.0
},
"calibration_bridge": {
"best_calibrated_model": "claude-opus-5",
"brier": 0.2677,
"hit_rate_leader": "claude-opus-5"
},
"asset_league": {
"by_symbol": [
{
"n": 3857,
"hit_rate": 0.4807,
"wilson_95": [
0.4649,
0.4965
],
"insufficient": false,
"symbol": "BNB",
"rank": 1
},
{
"n": 3928,
"hit_rate": 0.4733,
"wilson_95": [
0.4577,
0.4889
],
"insufficient": false,
"symbol": "SOL",
"rank": 2
},
{
"n": 3835,
"hit_rate": 0.4673,
"wilson_95": [
0.4515,
0.4831
],
"insufficient": false,
"symbol": "XRP",
"rank": 3
},
{
"n": 4068,
"hit_rate": 0.4648,
"wilson_95": [
0.4496,
0.4802
],
"insufficient": false,
"symbol": "BTC",
"rank": 4
},
{
"n": 3695,
"hit_rate": 0.4287,
"wilson_95": [
0.4128,
0.4447
],
"insufficient": false,
"symbol": "ETH",
"rank": 5
}
],
"by_symbol_fh": {
"BTC": {
"fh_1h": {
"n": 2502,
"hit_rate": 0.4648,
"wilson_95": [
0.4454,
0.4844
],
"insufficient": false
},
"fh_4h": {
"n": 1327,
"hit_rate": 0.4484,
"wilson_95": [
0.4218,
0.4752
],
"insufficient": false
},
"fh_1d": {
"n": 239,
"hit_rate": 0.5565,
"wilson_95": [
0.4931,
0.6181
],
"insufficient": false
}
},
"ETH": {
"fh_1h": {
"n": 2377,
"hit_rate": 0.4434,
"wilson_95": [
0.4236,
0.4635
],
"insufficient": false
},
"fh_4h": {
"n": 1122,
"hit_rate": 0.3966,
"wilson_95": [
0.3684,
0.4255
],
"insufficient": false
},
"fh_1d": {
"n": 196,
"hit_rate": 0.4337,
"wilson_95": [
0.3662,
0.5037
],
"insufficient": false
}
},
"SOL": {
"fh_1h": {
"n": 2440,
"hit_rate": 0.4533,
"wilson_95": [
0.4336,
0.4731
],
"insufficient": false
},
"fh_4h": {
"n": 1266,
"hit_rate": 0.4897,
"wilson_95": [
0.4623,
0.5173
],
"insufficient": false
},
"fh_1d": {
"n": 222,
"hit_rate": 0.5991,
"wilson_95": [
0.5335,
0.6614
],
"insufficient": false
}
},
"BNB": {
"fh_1h": {
"n": 2364,
"hit_rate": 0.481,
"wilson_95": [
0.4609,
0.5011
],
"insufficient": false
},
"fh_4h": {
"n": 1244,
"hit_rate": 0.4936,
"wilson_95": [
0.4658,
0.5213
],
"insufficient": false
},
"fh_1d": {
"n": 249,
"hit_rate": 0.4137,
"wilson_95": [
0.3542,
0.4757
],
"insufficient": false
}
},
"XRP": {
"fh_1h": {
"n": 2427,
"hit_rate": 0.4644,
"wilson_95": [
0.4446,
0.4842
],
"insufficient": false
},
"fh_4h": {
"n": 1166,
"hit_rate": 0.4717,
"wilson_95": [
0.4432,
0.5004
],
"insufficient": false
},
"fh_1d": {
"n": 242,
"hit_rate": 0.4752,
"wilson_95": [
0.4132,
0.538
],
"insufficient": false
}
}
},
"by_week_symbol_published": {
"W1": [
{
"symbol": "SOL",
"n": 852,
"hit_rate": 0.4824,
"wilson_95": [
0.449,
0.516
],
"rank": 1
},
{
"symbol": "XRP",
"n": 800,
"hit_rate": 0.465,
"wilson_95": [
0.4307,
0.4996
],
"rank": 2
},
{
"symbol": "BNB",
"n": 782,
"hit_rate": 0.4361,
"wilson_95": [
0.4017,
0.471
],
"rank": 3
},
{
"symbol": "BTC",
"n": 884,
"hit_rate": 0.3835,
"wilson_95": [
0.352,
0.416
],
"rank": 4
},
{
"symbol": "ETH",
"n": 724,
"hit_rate": 0.3481,
"wilson_95": [
0.3143,
0.3835
],
"rank": 5
}
],
"W2": [
{
"symbol": "BNB",
"n": 816,
"hit_rate": 0.4926,
"wilson_95": [
0.4585,
0.5269
],
"rank": 1
},
{
"symbol": "XRP",
"n": 824,
"hit_rate": 0.4854,
"wilson_95": [
0.4515,
0.5196
],
"rank": 2
},
{
"symbol": "BTC",
"n": 727,
"hit_rate": 0.4402,
"wilson_95": [
0.4045,
0.4765
],
"rank": 3
},
{
"symbol": "SOL",
"n": 659,
"hit_rate": 0.3885,
"wilson_95": [
0.352,
0.4262
],
"rank": 4
},
{
"symbol": "ETH",
"n": 644,
"hit_rate": 0.3556,
"wilson_95": [
0.3196,
0.3933
],
"rank": 5
}
],
"W3": [
{
"symbol": "BTC",
"n": 1118,
"hit_rate": 0.5751,
"wilson_95": [
0.5459,
0.6038
],
"rank": 1
},
{
"symbol": "SOL",
"n": 1036,
"hit_rate": 0.5434,
"wilson_95": [
0.513,
0.5736
],
"rank": 2
},
{
"symbol": "BNB",
"n": 932,
"hit_rate": 0.5397,
"wilson_95": [
0.5076,
0.5715
],
"rank": 3
},
{
"symbol": "ETH",
"n": 1074,
"hit_rate": 0.5279,
"wilson_95": [
0.498,
0.5576
],
"rank": 4
},
{
"symbol": "XRP",
"n": 970,
"hit_rate": 0.5124,
"wilson_95": [
0.4809,
0.5437
],
"rank": 5
}
],
"W4": [
{
"symbol": "SOL",
"n": 1025,
"hit_rate": 0.4576,
"wilson_95": [
0.4273,
0.4882
],
"rank": 1
},
{
"symbol": "BTC",
"n": 940,
"hit_rate": 0.4372,
"wilson_95": [
0.4058,
0.4691
],
"rank": 2
},
{
"symbol": "ETH",
"n": 827,
"hit_rate": 0.4329,
"wilson_95": [
0.3995,
0.4669
],
"rank": 3
},
{
"symbol": "BNB",
"n": 895,
"hit_rate": 0.4123,
"wilson_95": [
0.3805,
0.4448
],
"rank": 4
},
{
"symbol": "XRP",
"n": 889,
"hit_rate": 0.4027,
"wilson_95": [
0.3709,
0.4353
],
"rank": 5
}
]
},
"by_week_symbol": {
"W1": [
{
"n": 852,
"hit_rate": 0.4824,
"wilson_95": [
0.449,
0.516
],
"insufficient": false,
"symbol": "SOL",
"rank": 1
},
{
"n": 800,
"hit_rate": 0.465,
"wilson_95": [
0.4307,
0.4996
],
"insufficient": false,
"symbol": "XRP",
"rank": 2
},
{
"n": 782,
"hit_rate": 0.4361,
"wilson_95": [
0.4017,
0.471
],
"insufficient": false,
"symbol": "BNB",
"rank": 3
},
{
"n": 884,
"hit_rate": 0.3835,
"wilson_95": [
0.352,
0.416
],
"insufficient": false,
"symbol": "BTC",
"rank": 4
},
{
"n": 724,
"hit_rate": 0.3481,
"wilson_95": [
0.3143,
0.3835
],
"insufficient": false,
"symbol": "ETH",
"rank": 5
}
],
"W2": [
{
"n": 816,
"hit_rate": 0.4926,
"wilson_95": [
0.4585,
0.5269
],
"insufficient": false,
"symbol": "BNB",
"rank": 1
},
{
"n": 824,
"hit_rate": 0.4854,
"wilson_95": [
0.4515,
0.5196
],
"insufficient": false,
"symbol": "XRP",
"rank": 2
},
{
"n": 727,
"hit_rate": 0.4402,
"wilson_95": [
0.4045,
0.4765
],
"insufficient": false,
"symbol": "BTC",
"rank": 3
},
{
"n": 659,
"hit_rate": 0.3885,
"wilson_95": [
0.352,
0.4262
],
"insufficient": false,
"symbol": "SOL",
"rank": 4
},
{
"n": 644,
"hit_rate": 0.3556,
"wilson_95": [
0.3196,
0.3933
],
"insufficient": false,
"symbol": "ETH",
"rank": 5
}
],
"W3": [
{
"n": 1118,
"hit_rate": 0.5751,
"wilson_95": [
0.5459,
0.6038
],
"insufficient": false,
"symbol": "BTC",
"rank": 1
},
{
"n": 1036,
"hit_rate": 0.5434,
"wilson_95": [
0.513,
0.5736
],
"insufficient": false,
"symbol": "SOL",
"rank": 2
},
{
"n": 932,
"hit_rate": 0.5397,
"wilson_95": [
0.5076,
0.5715
],
"insufficient": false,
"symbol": "BNB",
"rank": 3
},
{
"n": 1074,
"hit_rate": 0.5279,
"wilson_95": [
0.498,
0.5576
],
"insufficient": false,
"symbol": "ETH",
"rank": 4
},
{
"n": 970,
"hit_rate": 0.5124,
"wilson_95": [
0.4809,
0.5437
],
"insufficient": false,
"symbol": "XRP",
"rank": 5
}
],
"W4": [
{
"n": 1025,
"hit_rate": 0.4576,
"wilson_95": [
0.4273,
0.4882
],
"insufficient": false,
"symbol": "SOL",
"rank": 1
},
{
"n": 940,
"hit_rate": 0.4372,
"wilson_95": [
0.4058,
0.4691
],
"insufficient": false,
"symbol": "BTC",
"rank": 2
},
{
"n": 827,
"hit_rate": 0.4329,
"wilson_95": [
0.3995,
0.4669
],
"insufficient": false,
"symbol": "ETH",
"rank": 3
},
{
"n": 895,
"hit_rate": 0.4123,
"wilson_95": [
0.3805,
0.4448
],
"insufficient": false,
"symbol": "BNB",
"rank": 4
},
{
"n": 889,
"hit_rate": 0.4027,
"wilson_95": [
0.3709,
0.4353
],
"insufficient": false,
"symbol": "XRP",
"rank": 5
}
]
},
"by_model_symbol": {
"claude-fable-5": {
"BTC": {
"n": 598,
"hit_rate": 0.4599
},
"ETH": {
"n": 529,
"hit_rate": 0.4405
},
"SOL": {
"n": 604,
"hit_rate": 0.4851
},
"BNB": {
"n": 582,
"hit_rate": 0.4759
},
"XRP": {
"n": 499,
"hit_rate": 0.4729
}
},
"claude-opus-5": {
"BTC": {
"n": 484,
"hit_rate": 0.4669
},
"ETH": {
"n": 430,
"hit_rate": 0.4651
},
"SOL": {
"n": 482,
"hit_rate": 0.5041
},
"BNB": {
"n": 447,
"hit_rate": 0.4855
},
"XRP": {
"n": 438,
"hit_rate": 0.4658
}
},
"deepseek-v4-pro": {
"BTC": {
"n": 552,
"hit_rate": 0.4656
},
"ETH": {
"n": 522,
"hit_rate": 0.4119
},
"SOL": {
"n": 499,
"hit_rate": 0.4629
},
"BNB": {
"n": 500,
"hit_rate": 0.472
},
"XRP": {
"n": 505,
"hit_rate": 0.4653
}
},
"gemini-3.1-pro": {
"BTC": {
"n": 647,
"hit_rate": 0.4683
},
"ETH": {
"n": 552,
"hit_rate": 0.4511
},
"SOL": {
"n": 626,
"hit_rate": 0.4665
},
"BNB": {
"n": 568,
"hit_rate": 0.4965
},
"XRP": {
"n": 640,
"hit_rate": 0.4969
}
},
"gpt-5.6-sol": {
"BTC": {
"n": 631,
"hit_rate": 0.4643
},
"ETH": {
"n": 574,
"hit_rate": 0.4164
},
"SOL": {
"n": 572,
"hit_rate": 0.4755
},
"BNB": {
"n": 604,
"hit_rate": 0.4669
},
"XRP": {
"n": 589,
"hit_rate": 0.4686
}
},
"grok-4.6": {
"BTC": {
"n": 544,
"hit_rate": 0.4779
},
"ETH": {
"n": 512,
"hit_rate": 0.4199
},
"SOL": {
"n": 535,
"hit_rate": 0.4486
},
"BNB": {
"n": 569,
"hit_rate": 0.4728
},
"XRP": {
"n": 548,
"hit_rate": 0.4416
}
},
"qwen-3.8-max": {
"BTC": {
"n": 612,
"hit_rate": 0.4526
},
"ETH": {
"n": 576,
"hit_rate": 0.4045
},
"SOL": {
"n": 610,
"hit_rate": 0.4721
},
"BNB": {
"n": 587,
"hit_rate": 0.4957
},
"XRP": {
"n": 616,
"hit_rate": 0.4562
}
}
},
"sol_hypothesis": {
"symbol": "SOL",
"month_rank": 2,
"month_n": 3928,
"month_hit_rate": 0.4733,
"weeks_ranked_first": [
"W1",
"W4"
],
"weeks_rank": {
"W1": 1,
"W2": 4,
"W3": 2,
"W4": 1
},
"weeks_rank_published": {
"W1": 1,
"W2": 4,
"W3": 2,
"W4": 1
},
"best_fh": "fh_1d",
"best_fh_hit_rate": 0.5991,
"note": "SOL: month rank 2 of 5 symbols (n=3928, hit_rate=0.4733, wilson_95=[0.4577, 0.4889]); rank 1 in 2 of 4 weeks (W1,W4); highest hit_rate by horizon fh_1d (n=222, hit_rate=0.5991). Ranks from the month pull split by slot week; published ranks from the weekly packs' ticker_of_week."
},
"rank_rule": "rank 1 = highest hit_rate; ties broken by n desc; empty cells rank last",
"source": "month_pull_split_by_slot_week (cutoff 2026-09-01T16:00:00+00:00)",
"by_week_symbol_published_source": "weeks.W*.model_watch.ticker_of_week (frozen weekly cutoffs)"
},
"rank_stability": {
"by_week": {
"W1": [
{
"model": "gemini-3.1-pro",
"rank": 1,
"n": 629,
"hit_rate": 0.4372,
"wilson_95": [
0.3989,
0.4762
],
"insufficient": false
},
{
"model": "qwen-3.8-max",
"rank": 2,
"n": 710,
"hit_rate": 0.4338,
"wilson_95": [
0.3978,
0.4705
],
"insufficient": false
},
{
"model": "gpt-5.6-sol",
"rank": 3,
"n": 612,
"hit_rate": 0.4297,
"wilson_95": [
0.3911,
0.4693
],
"insufficient": false
},
{
"model": "grok-4.6",
"rank": 4,
"n": 607,
"hit_rate": 0.4217,
"wilson_95": [
0.3831,
0.4614
],
"insufficient": false
},
{
"model": "deepseek-v4-pro",
"rank": 5,
"n": 377,
"hit_rate": 0.4164,
"wilson_95": [
0.3678,
0.4668
],
"insufficient": false
},
{
"model": "claude-fable-5",
"rank": 6,
"n": 642,
"hit_rate": 0.4143,
"wilson_95": [
0.3768,
0.4528
],
"insufficient": false
},
{
"model": "claude-opus-5",
"rank": 7,
"n": 465,
"hit_rate": 0.4086,
"wilson_95": [
0.3648,
0.4539
],
"insufficient": false
}
],
"W2": [
{
"model": "gemini-3.1-pro",
"rank": 1,
"n": 555,
"hit_rate": 0.4703,
"wilson_95": [
0.4291,
0.5119
],
"insufficient": false
},
{
"model": "gpt-5.6-sol",
"rank": 2,
"n": 636,
"hit_rate": 0.4418,
"wilson_95": [
0.4037,
0.4807
],
"insufficient": false
},
{
"model": "qwen-3.8-max",
"rank": 3,
"n": 572,
"hit_rate": 0.4406,
"wilson_95": [
0.4004,
0.4815
],
"insufficient": false
},
{
"model": "grok-4.6",
"rank": 4,
"n": 620,
"hit_rate": 0.4403,
"wilson_95": [
0.4017,
0.4796
],
"insufficient": false
},
{
"model": "deepseek-v4-pro",
"rank": 5,
"n": 454,
"hit_rate": 0.4251,
"wilson_95": [
0.3805,
0.471
],
"insufficient": false
},
{
"model": "claude-fable-5",
"rank": 6,
"n": 472,
"hit_rate": 0.4174,
"wilson_95": [
0.3737,
0.4624
],
"insufficient": false
},
{
"model": "claude-opus-5",
"rank": 7,
"n": 361,
"hit_rate": 0.4155,
"wilson_95": [
0.3658,
0.467
],
"insufficient": false
}
],
"W3": [
{
"model": "claude-opus-5",
"rank": 1,
"n": 672,
"hit_rate": 0.5908,
"wilson_95": [
0.5532,
0.6273
],
"insufficient": false
},
{
"model": "claude-fable-5",
"rank": 2,
"n": 779,
"hit_rate": 0.5648,
"wilson_95": [
0.5298,
0.5992
],
"insufficient": false
},
{
"model": "gemini-3.1-pro",
"rank": 3,
"n": 798,
"hit_rate": 0.5414,
"wilson_95": [
0.5067,
0.5756
],
"insufficient": false
},
{
"model": "gpt-5.6-sol",
"rank": 4,
"n": 688,
"hit_rate": 0.5363,
"wilson_95": [
0.499,
0.5733
],
"insufficient": false
},
{
"model": "qwen-3.8-max",
"rank": 5,
"n": 706,
"hit_rate": 0.5227,
"wilson_95": [
0.4858,
0.5593
],
"insufficient": false
},
{
"model": "deepseek-v4-pro",
"rank": 6,
"n": 777,
"hit_rate": 0.5161,
"wilson_95": [
0.481,
0.5511
],
"insufficient": false
},
{
"model": "grok-4.6",
"rank": 7,
"n": 710,
"hit_rate": 0.5141,
"wilson_95": [
0.4773,
0.5507
],
"insufficient": false
}
],
"W4": [
{
"model": "deepseek-v4-pro",
"rank": 1,
"n": 729,
"hit_rate": 0.4458,
"wilson_95": [
0.4101,
0.4821
],
"insufficient": false
},
{
"model": "gemini-3.1-pro",
"rank": 2,
"n": 755,
"hit_rate": 0.4424,
"wilson_95": [
0.4073,
0.478
],
"insufficient": false
},
{
"model": "claude-fable-5",
"rank": 3,
"n": 651,
"hit_rate": 0.4301,
"wilson_95": [
0.3926,
0.4684
],
"insufficient": false
},
{
"model": "gpt-5.6-sol",
"rank": 4,
"n": 729,
"hit_rate": 0.4266,
"wilson_95": [
0.3912,
0.4628
],
"insufficient": false
},
{
"model": "qwen-3.8-max",
"rank": 5,
"n": 672,
"hit_rate": 0.4256,
"wilson_95": [
0.3887,
0.4633
],
"insufficient": false
},
{
"model": "claude-opus-5",
"rank": 6,
"n": 561,
"hit_rate": 0.4242,
"wilson_95": [
0.384,
0.4655
],
"insufficient": false
},
{
"model": "grok-4.6",
"rank": 7,
"n": 479,
"hit_rate": 0.3987,
"wilson_95": [
0.3559,
0.4432
],
"insufficient": false
}
]
},
"month_rank": [
{
"model": "claude-opus-5",
"rank": 1,
"n": 2281,
"hit_rate": 0.4779,
"wilson_95": [
0.4574,
0.4984
],
"insufficient": false
},
{
"model": "gemini-3.1-pro",
"rank": 2,
"n": 3033,
"hit_rate": 0.4761,
"wilson_95": [
0.4584,
0.4939
],
"insufficient": false
},
{
"model": "claude-fable-5",
"rank": 3,
"n": 2812,
"hit_rate": 0.4673,
"wilson_95": [
0.4489,
0.4858
],
"insufficient": false
},
{
"model": "gpt-5.6-sol",
"rank": 4,
"n": 2970,
"hit_rate": 0.4586,
"wilson_95": [
0.4407,
0.4765
],
"insufficient": false
},
{
"model": "qwen-3.8-max",
"rank": 5,
"n": 3001,
"hit_rate": 0.4565,
"wilson_95": [
0.4388,
0.4744
],
"insufficient": false
},
{
"model": "deepseek-v4-pro",
"rank": 6,
"n": 2578,
"hit_rate": 0.4554,
"wilson_95": [
0.4362,
0.4747
],
"insufficient": false
},
{
"model": "grok-4.6",
"rank": 7,
"n": 2708,
"hit_rate": 0.4527,
"wilson_95": [
0.4341,
0.4715
],
"insufficient": false
}
],
"per_model": {
"claude-fable-5": {
"ranks": [
6,
6,
2,
3
],
"n": [
642,
472,
779,
651
],
"hit_rates": [
0.4143,
0.4174,
0.5648,
0.4301
],
"mean_rank": 4.25,
"best": 2,
"worst": 6,
"range": 4,
"month_rank": 3,
"month_hit_rate": 0.4673
},
"claude-opus-5": {
"ranks": [
7,
7,
1,
6
],
"n": [
465,
361,
672,
561
],
"hit_rates": [
0.4086,
0.4155,
0.5908,
0.4242
],
"mean_rank": 5.25,
"best": 1,
"worst": 7,
"range": 6,
"month_rank": 1,
"month_hit_rate": 0.4779
},
"deepseek-v4-pro": {
"ranks": [
5,
5,
6,
1
],
"n": [
377,
454,
777,
729
],
"hit_rates": [
0.4164,
0.4251,
0.5161,
0.4458
],
"mean_rank": 4.25,
"best": 1,
"worst": 6,
"range": 5,
"month_rank": 6,
"month_hit_rate": 0.4554
},
"gemini-3.1-pro": {
"ranks": [
1,
1,
3,
2
],
"n": [
629,
555,
798,
755
],
"hit_rates": [
0.4372,
0.4703,
0.5414,
0.4424
],
"mean_rank": 1.75,
"best": 1,
"worst": 3,
"range": 2,
"month_rank": 2,
"month_hit_rate": 0.4761
},
"gpt-5.6-sol": {
"ranks": [
3,
2,
4,
4
],
"n": [
612,
636,
688,
729
],
"hit_rates": [
0.4297,
0.4418,
0.5363,
0.4266
],
"mean_rank": 3.25,
"best": 2,
"worst": 4,
"range": 2,
"month_rank": 4,
"month_hit_rate": 0.4586
},
"grok-4.6": {
"ranks": [
4,
4,
7,
7
],
"n": [
607,
620,
710,
479
],
"hit_rates": [
0.4217,
0.4403,
0.5141,
0.3987
],
"mean_rank": 5.5,
"best": 4,
"worst": 7,
"range": 3,
"month_rank": 7,
"month_hit_rate": 0.4527
},
"qwen-3.8-max": {
"ranks": [
2,
3,
5,
5
],
"n": [
710,
572,
706,
672
],
"hit_rates": [
0.4338,
0.4406,
0.5227,
0.4256
],
"mean_rank": 3.75,
"best": 2,
"worst": 5,
"range": 3,
"month_rank": 5,
"month_hit_rate": 0.4565
}
},
"spearman_consecutive": [
{
"pair": "W1-W2",
"rho": 0.9643
},
{
"pair": "W2-W3",
"rho": -0.3214
},
{
"pair": "W3-W4",
"rho": 0.0714
}
],
"spearman_vs_month": {
"W1": -0.1786,
"W2": -0.1429,
"W3": 0.9643,
"W4": 0.1071
},
"top_model_by_week": {
"W1": "gemini-3.1-pro",
"W2": "gemini-3.1-pro",
"W3": "claude-opus-5",
"W4": "deepseek-v4-pro"
},
"n_distinct_leaders": 3,
"rank_rule": "rank = position in the pack's leaderboard, which w201 sorts by hit_rate desc",
"spearman_note": "rho computed here (no scipy on the box); ties get average ranks",
"source": "weekly packs model_watch.leaderboard.rows (frozen cutoffs) + MONTH pack",
"widths_mm_used": [
40,
17,
17,
17,
17,
20,
24,
22
]
},
"regime_weeks": {
"per_week": {
"W1": {
"label_window": "Aug 3-9",
"days_in_week": 7,
"days_with_price": 7,
"mean_abs_1d_move_pct": 0.529,
"max_abs_1d_move_pct": 0.98,
"trend_days": 0,
"flat_days": 7,
"daily_moves_pct": {
"2026-08-03": 0.09,
"2026-08-04": 0.93,
"2026-08-05": 0.98,
"2026-08-06": -0.57,
"2026-08-07": 0.88,
"2026-08-08": 0.16,
"2026-08-09": 0.09
},
"label": "calm"
},
"W2": {
"label_window": "Aug 10-16",
"days_in_week": 7,
"days_with_price": 7,
"mean_abs_1d_move_pct": 0.507,
"max_abs_1d_move_pct": 1.63,
"trend_days": 1,
"flat_days": 6,
"daily_moves_pct": {
"2026-08-10": -1.63,
"2026-08-11": -0.56,
"2026-08-12": -0.02,
"2026-08-13": -0.25,
"2026-08-14": -0.67,
"2026-08-15": 0.07,
"2026-08-16": -0.35
},
"label": "calm"
},
"W3": {
"label_window": "Aug 17-23",
"days_in_week": 7,
"days_with_price": 7,
"mean_abs_1d_move_pct": 3.61,
"max_abs_1d_move_pct": 7.82,
"trend_days": 5,
"flat_days": 2,
"daily_moves_pct": {
"2026-08-17": 2.55,
"2026-08-18": 0.21,
"2026-08-19": 7.82,
"2026-08-20": 5.07,
"2026-08-21": 7.26,
"2026-08-22": -1.67,
"2026-08-23": 0.69
},
"label": "volatile"
},
"W4": {
"label_window": "Aug 24-30",
"days_in_week": 7,
"days_with_price": 7,
"mean_abs_1d_move_pct": 1.206,
"max_abs_1d_move_pct": 2.91,
"trend_days": 3,
"flat_days": 4,
"daily_moves_pct": {
"2026-08-24": 1.61,
"2026-08-25": -0.58,
"2026-08-26": 0.63,
"2026-08-27": 1.53,
"2026-08-28": -2.91,
"2026-08-29": 0.48,
"2026-08-30": -0.7
},
"label": "volatile"
}
},
"week_labels": {
"W1": "calm",
"W2": "calm",
"W3": "volatile",
"W4": "volatile"
},
"per_model": {
"claude-fable-5": {
"calm": {
"n": 1114,
"hit_rate": 0.4156,
"wilson_95": [
0.387,
0.4448
],
"insufficient": false
},
"volatile": {
"n": 1430,
"hit_rate": 0.5035,
"wilson_95": [
0.4776,
0.5294
],
"insufficient": false
},
"diff_pp": 8.8
},
"claude-opus-5": {
"calm": {
"n": 826,
"hit_rate": 0.4116,
"wilson_95": [
0.3785,
0.4455
],
"insufficient": false
},
"volatile": {
"n": 1233,
"hit_rate": 0.515,
"wilson_95": [
0.4871,
0.5428
],
"insufficient": false
},
"diff_pp": 10.3
},
"deepseek-v4-pro": {
"calm": {
"n": 831,
"hit_rate": 0.4212,
"wilson_95": [
0.388,
0.455
],
"insufficient": false
},
"volatile": {
"n": 1506,
"hit_rate": 0.4821,
"wilson_95": [
0.4569,
0.5073
],
"insufficient": false
},
"diff_pp": 6.1
},
"gemini-3.1-pro": {
"calm": {
"n": 1184,
"hit_rate": 0.4527,
"wilson_95": [
0.4245,
0.4812
],
"insufficient": false
},
"volatile": {
"n": 1553,
"hit_rate": 0.4932,
"wilson_95": [
0.4684,
0.5181
],
"insufficient": false
},
"diff_pp": 4.1
},
"gpt-5.6-sol": {
"calm": {
"n": 1248,
"hit_rate": 0.4359,
"wilson_95": [
0.4086,
0.4636
],
"insufficient": false
},
"volatile": {
"n": 1417,
"hit_rate": 0.4799,
"wilson_95": [
0.454,
0.5059
],
"insufficient": false
},
"diff_pp": 4.4
},
"grok-4.6": {
"calm": {
"n": 1227,
"hit_rate": 0.4311,
"wilson_95": [
0.4037,
0.459
],
"insufficient": false
},
"volatile": {
"n": 1189,
"hit_rate": 0.4676,
"wilson_95": [
0.4394,
0.496
],
"insufficient": false
},
"diff_pp": 3.7
},
"qwen-3.8-max": {
"calm": {
"n": 1282,
"hit_rate": 0.4368,
"wilson_95": [
0.4099,
0.4641
],
"insufficient": false
},
"volatile": {
"n": 1378,
"hit_rate": 0.4753,
"wilson_95": [
0.4491,
0.5017
],
"insufficient": false
},
"diff_pp": 3.8
}
},
"field": {
"calm": {
"n": 7712,
"hit_rate": 0.4308,
"wilson_95": [
0.4197,
0.4418
],
"insufficient": false
},
"volatile": {
"n": 9706,
"hit_rate": 0.4882,
"wilson_95": [
0.4782,
0.4981
],
"insufficient": false
},
"diff_pp": 5.7
},
"rule": "label = 'volatile' if mean_abs_1d_move_pct >= median of the four weeks else 'calm'",
"median_mean_abs_1d_move_pct": 0.867,
"diff_definition": "diff_pp = volatile hit_rate - calm hit_rate, in percentage points",
"trend_day_rule": "w201 regime_days: |BTC 1d move| >= 1.5% -> trend, else flat",
"rows_outside_weeks": 1965
},
"prior_window_model_watch": {
"leaderboard": [
{
"model": "qwen-3.8-max",
"n": 3371,
"hit_rate": 0.4568,
"wilson_95": [
0.4401,
0.4737
],
"coverage": 0.5347,
"insufficient": false
},
{
"model": "grok-4.6",
"n": 2265,
"hit_rate": 0.453,
"wilson_95": [
0.4326,
0.4735
],
"coverage": 0.5333,
"insufficient": false
},
{
"model": "gemini-3.1-pro",
"n": 2813,
"hit_rate": 0.4511,
"wilson_95": [
0.4328,
0.4696
],
"coverage": 0.454,
"insufficient": false
},
{
"model": "deepseek-v4-pro",
"n": 1869,
"hit_rate": 0.4505,
"wilson_95": [
0.4281,
0.4731
],
"coverage": 0.296,
"insufficient": false
},
{
"model": "claude-opus-5",
"n": 3448,
"hit_rate": 0.4492,
"wilson_95": [
0.4327,
0.4659
],
"coverage": 0.5475,
"insufficient": false
},
{
"model": "claude-fable-5",
"n": 2690,
"hit_rate": 0.445,
"wilson_95": [
0.4263,
0.4638
],
"coverage": 0.4263,
"insufficient": false
},
{
"model": "gpt-5.6-sol",
"n": 3085,
"hit_rate": 0.4431,
"wilson_95": [
0.4257,
0.4607
],
"coverage": 0.4885,
"insufficient": false
}
],
"by_symbol": [
{
"symbol": "ETH",
"n": 4564,
"hit_rate": 0.4781,
"wilson_95": [
0.4636,
0.4926
]
},
{
"symbol": "BNB",
"n": 2720,
"hit_rate": 0.4548,
"wilson_95": [
0.4361,
0.4735
]
},
{
"symbol": "XRP",
"n": 3053,
"hit_rate": 0.4455,
"wilson_95": [
0.4279,
0.4632
]
},
{
"symbol": "BTC",
"n": 4169,
"hit_rate": 0.4418,
"wilson_95": [
0.4268,
0.457
]
},
{
"symbol": "SOL",
"n": 3443,
"hit_rate": 0.4325,
"wilson_95": [
0.416,
0.4491
]
}
],
"by_model_symbol": {
"claude-fable-5": {
"BTC": {
"n": 587,
"hit_rate": 0.4395
},
"ETH": {
"n": 642,
"hit_rate": 0.4782
},
"SOL": {
"n": 490,
"hit_rate": 0.4204
},
"BNB": {
"n": 358,
"hit_rate": 0.4637
},
"XRP": {
"n": 393,
"hit_rate": 0.43
}
},
"claude-opus-5": {
"BTC": {
"n": 798,
"hit_rate": 0.4411
},
"ETH": {
"n": 799,
"hit_rate": 0.4768
},
"SOL": {
"n": 573,
"hit_rate": 0.4398
},
"BNB": {
"n": 476,
"hit_rate": 0.4538
},
"XRP": {
"n": 507,
"hit_rate": 0.4517
}
},
"deepseek-v4-pro": {
"BTC": {
"n": 397,
"hit_rate": 0.4509
},
"ETH": {
"n": 477,
"hit_rate": 0.4528
},
"SOL": {
"n": 319,
"hit_rate": 0.4044
},
"BNB": {
"n": 260,
"hit_rate": 0.4654
},
"XRP": {
"n": 279,
"hit_rate": 0.4839
}
},
"gemini-3.1-pro": {
"BTC": {
"n": 600,
"hit_rate": 0.4583
},
"ETH": {
"n": 609,
"hit_rate": 0.4647
},
"SOL": {
"n": 489,
"hit_rate": 0.4335
},
"BNB": {
"n": 415,
"hit_rate": 0.4578
},
"XRP": {
"n": 433,
"hit_rate": 0.4434
}
},
"gpt-5.6-sol": {
"BTC": {
"n": 615,
"hit_rate": 0.4293
},
"ETH": {
"n": 706,
"hit_rate": 0.4731
},
"SOL": {
"n": 549,
"hit_rate": 0.4153
},
"BNB": {
"n": 446,
"hit_rate": 0.4439
},
"XRP": {
"n": 528,
"hit_rate": 0.4489
}
},
"grok-4.6": {
"BTC": {
"n": 447,
"hit_rate": 0.4497
},
"ETH": {
"n": 520,
"hit_rate": 0.4885
},
"SOL": {
"n": 435,
"hit_rate": 0.4552
},
"BNB": {
"n": 296,
"hit_rate": 0.4426
},
"XRP": {
"n": 390,
"hit_rate": 0.4282
}
},
"qwen-3.8-max": {
"BTC": {
"n": 725,
"hit_rate": 0.4317
},
"ETH": {
"n": 811,
"hit_rate": 0.5018
},
"SOL": {
"n": 588,
"hit_rate": 0.449
},
"BNB": {
"n": 469,
"hit_rate": 0.4584
},
"XRP": {
"n": 523,
"hit_rate": 0.4417
}
}
},
"side_mix": [
{
"model": "claude-fable-5",
"n": 6329,
"long": 0.2828,
"short": 0.1452,
"sideways": 0.572
},
{
"model": "claude-opus-5",
"n": 6329,
"long": 0.3332,
"short": 0.2165,
"sideways": 0.4503
},
{
"model": "deepseek-v4-pro",
"n": 6332,
"long": 0.1361,
"short": 0.1619,
"sideways": 0.702
},
{
"model": "gemini-3.1-pro",
"n": 6211,
"long": 0.2541,
"short": 0.2013,
"sideways": 0.5447
},
{
"model": "gpt-5.6-sol",
"n": 6335,
"long": 0.2423,
"short": 0.2478,
"sideways": 0.5099
},
{
"model": "grok-4.6",
"n": 4271,
"long": 0.2035,
"short": 0.3325,
"sideways": 0.4641
},
{
"model": "qwen-3.8-max",
"n": 6327,
"long": 0.2828,
"short": 0.2535,
"sideways": 0.4637
}
],
"symbols": [
"BTC",
"ETH",
"SOL",
"BNB",
"XRP"
],
"models": [
"claude-fable-5",
"claude-opus-5",
"deepseek-v4-pro",
"gemini-3.1-pro",
"gpt-5.6-sol",
"grok-4.6",
"qwen-3.8-max"
],
"side_mix_source": "ok in-gate rows of the window (w201 model_watch.side_mix definition)",
"symbols_compared": [
"BNB",
"SOL",
"XRP",
"BTC",
"ETH"
],
"symbols_prior_window_all": [
"BTC",
"ETH",
"SOL",
"BNB",
"XRP",
"LINK",
"PEPE",
"AVAX",
"DOGE",
"TON"
],
"symbols_retired_not_compared": [
"AVAX",
"DOGE",
"LINK",
"PEPE",
"TON"
],
"coin_set_rule": "only the current five assets are compared; coins the prior window carried but the month does not are listed here by name only"
},
"verdict_block": {
"rule": "Verdict rule: each row states one reading of the month; a week agrees when it shows the same reading (same sign, or the same name). Confirmed = 3 or 4 of the 4 weeks agree with the month; Inconclusive = 2; Rejected = 0 or 1. Weekly cells come from the frozen weekly packs (7-line roster, lineage spliced); the month is the pooled Aug 1-31 pull.",
"header": [
"Metric",
"W1 Aug 3-9",
"W2 Aug 10-16",
"W3 Aug 17-23",
"W4 Aug 24-30",
"Month",
"Verdict"
],
"widths_mm": [
36,
23,
23,
23,
23,
18,
28
],
"weeks_source": "frozen weekly packs (weeks.W1..W4 of the monthly pack, 7-line roster, lineage spliced)",
"month_source": "the pooled Aug 1-31 pull (month block)",
"rows": [
{
"metric": "Leader (hit-rate)",
"weeks": {
"W1": {
"value": "gemini-3.1",
"reading": "gemini-3.1-pro"
},
"W2": {
"value": "gemini-3.1",
"reading": "gemini-3.1-pro"
},
"W3": {
"value": "opus-5",
"reading": "claude-opus-5"
},
"W4": {
"value": "deepseek",
"reading": "deepseek-v4-pro"
}
},
"month": {
"value": "opus-5",
"reading": "claude-opus-5"
},
"agree_count": 1,
"verdict": "Rejected (1/4)"
},
{
"metric": "Most readable coin",
"weeks": {
"W1": {
"value": "SOL",
"reading": "SOL"
},
"W2": {
"value": "BNB",
"reading": "BNB"
},
"W3": {
"value": "BTC",
"reading": "BTC"
},
"W4": {
"value": "SOL",
"reading": "SOL"
}
},
"month": {
"value": "BNB",
"reading": "BNB"
},
"agree_count": 1,
"verdict": "Rejected (1/4)"
},
{
"metric": "Field hit below 50%",
"weeks": {
"W1": {
"value": "42.4%",
"reading": "below 50%"
},
"W2": {
"value": "43.8%",
"reading": "below 50%"
},
"W3": {
"value": "54.0%",
"reading": "at or above 50%"
},
"W4": {
"value": "42.9%",
"reading": "below 50%"
}
},
"month": {
"value": "46.3%",
"reading": "below 50%"
},
"agree_count": 3,
"verdict": "Confirmed (3/4)"
}
]
}
},
"key_findings": [
"**OBSERVATION -- No monthly title.** claude-opus-5 leads the month descriptively at 47.8% [45.7%, 49.8%]; the gap to #2 (gemini-3.1-pro, 47.6%) is 0.2pp. 5 of 7 models improved against the partial July, and 3 distinct model lines held the weekly top spot across the four weeks.",
"**No ticker cleared 51%.** BNB is the month's most readable coin (48.1%, n=3,857) and ETH the hardest at 42.9%; 0 of the 5 assets cleared 51% over the month. Pair of the month: claude-opus-5 x SOL 50.4% (n=482); worst: qwen-3.8-max (spliced) x ETH 40.5% (n=576).",
"**Mean weekly rank ran 1.75 to 5.50 across the four weeks.** claude-opus-5 swung across 6 rank positions and gemini-3.1-pro across 2. Consecutive-week Spearman came in at W1-W2 0.96, W2-W3 -0.32, W3-W4 0.07.",
"**The field read volatile weeks better.** Split by the pack's own volatility rule the field hit 43.1% (n=7,712) in the two calm weeks against 48.8% (n=9,706) in the two volatile ones, a difference of +5.7pp. Cross-TF/FH lifts ran -5.6pp to -0.6pp. On trend days, 4h TF-agreement hit 56.6% (n=749) against 39.0% (n=1,240) on flat days."
],
"market_check": {
"label": "MARKET CHECK · OBSERVATION (August against the partial July)",
"text": "OBSERVATION — mean |1d move| 1.54% -> 1.98% (+29% rel), BTC realized vol 33.5% -> 36.9% (ann., hourly); field directional accuracy 45.0% -> 46.3% (+1.4pp), 5 of 7 models improved, sim win-rate up for 7 of 7, field sim PnL -$3095.02 -> -$1054.79 (Jul 11-31 (partial) vs Aug 1-31; descriptive, one pair of windows, not a claim).",
"robustness": "Robustness: raw price-sign accuracy 46.8% -> 46.0% — the same direction as the trade-based hit rule.",
"weeks": {
"A": {
"days": "2026-07-01..2026-07-31",
"slots": [
"2026-07-01T00:00:00+00:00",
"2026-08-01T00:00:00+00:00"
],
"cutoff": "2026-08-01T16:00:00+00:00",
"partial": true
},
"B": {
"days": "2026-08-01..2026-08-31",
"slots": [
"2026-08-01T00:00:00+00:00",
"2026-09-01T00:00:00+00:00"
],
"cutoff": "2026-09-01T16:00:00+00:00"
}
},
"price_source": "crypto_spot/1h@:00",
"accuracy_field": {
"A": {
"n": 19541,
"hit_rate": 0.4498,
"wilson_95": [
0.4429,
0.4568
]
},
"B": {
"n": 19383,
"hit_rate": 0.4633,
"wilson_95": [
0.4563,
0.4703
]
},
"delta_pp": 1.4
},
"accuracy_per_model": [
{
"model": "claude-opus-5",
"model_label": "claude-opus-5",
"A": {
"n": 3448,
"hit_rate": 0.4492,
"wilson_95": [
0.4327,
0.4659
]
},
"B": {
"n": 2281,
"hit_rate": 0.4779,
"wilson_95": [
0.4574,
0.4984
]
},
"delta_pp": 2.9
},
{
"model": "gemini-3.1-pro",
"model_label": "gemini-3.1-pro",
"A": {
"n": 2813,
"hit_rate": 0.4511,
"wilson_95": [
0.4328,
0.4696
]
},
"B": {
"n": 3033,
"hit_rate": 0.4761,
"wilson_95": [
0.4584,
0.4939
]
},
"delta_pp": 2.5
},
{
"model": "claude-fable-5",
"model_label": "claude-fable-5",
"A": {
"n": 2690,
"hit_rate": 0.445,
"wilson_95": [
0.4263,
0.4638
]
},
"B": {
"n": 2812,
"hit_rate": 0.4673,
"wilson_95": [
0.4489,
0.4858
]
},
"delta_pp": 2.2
},
{
"model": "gpt-5.6-sol",
"model_label": "gpt-5.6-sol",
"A": {
"n": 3085,
"hit_rate": 0.4431,
"wilson_95": [
0.4257,
0.4607
]
},
"B": {
"n": 2970,
"hit_rate": 0.4586,
"wilson_95": [
0.4407,
0.4765
]
},
"delta_pp": 1.6
},
{
"model": "deepseek-v4-pro",
"model_label": "deepseek-v4-pro",
"A": {
"n": 1869,
"hit_rate": 0.4505,
"wilson_95": [
0.4281,
0.4731
]
},
"B": {
"n": 2578,
"hit_rate": 0.4554,
"wilson_95": [
0.4362,
0.4747
]
},
"delta_pp": 0.5
},
{
"model": "grok-4.6",
"model_label": "grok-4.6 (incl. 4.5-era, Aug 1-24)",
"A": {
"n": 2265,
"hit_rate": 0.453,
"wilson_95": [
0.4326,
0.4735
]
},
"B": {
"n": 2708,
"hit_rate": 0.4527,
"wilson_95": [
0.4341,
0.4715
]
},
"delta_pp": -0.0
},
{
"model": "qwen-3.8-max",
"model_label": "qwen-3.8-max (incl. 3.7-era, Aug 1-5)",
"A": {
"n": 3371,
"hit_rate": 0.4568,
"wilson_95": [
0.4401,
0.4737
]
},
"B": {
"n": 3001,
"hit_rate": 0.4565,
"wilson_95": [
0.4388,
0.4744
]
},
"delta_pp": -0.0
}
],
"raw_sign_field": {
"A": {
"n_scored": 17840,
"hit_rate": 0.4684
},
"B": {
"n_scored": 19304,
"hit_rate": 0.4599
}
},
"abs_move_1d": {
"A": 1.536,
"B": 1.979,
"delta_pct_rel": 28.8
},
"btc_realized_vol_ann_pct_hourly": {
"A": 33.46,
"B": 36.92
},
"trading_field": {
"A": {
"n_trades": 19541,
"wr": 0.3188,
"pnl_net_usd": -3095.02,
"pnl_gross_usd": -1140.92
},
"B": {
"n_trades": 19383,
"wr": 0.3576,
"pnl_net_usd": -1054.79,
"pnl_gross_usd": 883.51
}
},
"verdict": {
"models_with_hit_improved": "5 of 7",
"models_with_rawsign_improved": "1 of 7",
"models_with_wr_improved": "7 of 7",
"field_hit_delta_pp": 1.4,
"field_pnl_net": {
"A": -3095.02,
"B": -1054.79
},
"abs_move_delta": {
"1h": {
"A": 0.288,
"B": 0.325,
"delta_pct_rel": 12.8
},
"4h": {
"A": 0.557,
"B": 0.724,
"delta_pct_rel": 30.0
},
"1d": {
"A": 1.536,
"B": 1.979,
"delta_pct_rel": 28.8
}
},
"btc_vol_ann_pct": {
"A": 33.46,
"B": 36.92
},
"note": "descriptive, two adjacent windows; hit rule = methodology v1.1 trade-based; raw_sign = price-sign robustness check (closes at :00 vs slots at :01)"
},
"lineage_note": "lineage splice ACTIVE for all 7 heads: [('claude-opus-4.8', 'claude-opus-5'), ('grok-4.5', 'grok-4.6'), ('qwen-3.7-max', 'qwen-3.8-max')]. Window MONTH remapped 5390 row(s), the previous window 19532. Labels are generated from the pulled rows (see lineage_era).",
"prior_window_partial": true
},
"why_it_matters": "MarketMania scores 7 model lines against the same market, hour after hour. Monthly Model Watch asks the weekly questions at monthly n -- who led, which tickers were readable, who saw the turn first, does self-agreement help -- and then asks the three questions a single week cannot answer: which coin the field reads best over a month, how far a weekly rank moves inside one month, and how the field's accuracy differs between the calm and volatile weeks the pack labels. Each block gets its own table, its own N and its own caveats.",
"how_to_read_this": "Every block below is scored on the same pool: matured directional calls inside the 1h/4h/1d FH gate, hit by the methodology v1.1 direction rule, over the whole month at one cutoff (Mon Sep 1, 2026, 16:00 UTC). The monthly title is awarded only on a >=5pp gap AND non-overlapping 95% Wilson CIs with N>=10 per side -- a descriptive lead is not a title. Reversals use the 4h grid with a >=2.0% counter-move sustained 8h, BTC/ETH only in v1. Cross-TF/FH blocks ask whether a model agreeing with itself does any better, and are split trend vs flat. The by-week blocks come from the four frozen weekly packs at their own published cutoffs. 2 model lines are lineage splices this month (grok-4.6 (incl. 4.5-era, Aug 1-24); qwen-3.8-max (incl. 3.7-era, Aug 1-5)).",
"practical_implications": [
"On this month's leaderboard no title was awarded, the top two CIs overlap, and 3 distinct model lines led the four weeks inside the same month.",
"BNB ranked #1 for the month on n=3,857; the week-by-week league shows it ranked #1 in 1 of the four published weeks.",
"The field differs by +5.7pp between the two regimes on n=7,712 calm vs n=9,706 volatile; the rule that draws the line is the pack's own four-week median, recomputed every month."
],
"limitations": [
"The prior window is a PARTIAL month: forecasts run only from Jul 11 and the audited daily candles only from Jul 15, so every \"prior\" column, the gray series of the page-1 chart and the market-check A column describe Jul 11-31 (partial), not a full July. It is window A of the same pull, slots 2026-07-01 to 2026-08-01, forecasts counted from Jul 11 (first slot actually seen 2026-07-15 18:01 UTC) and audited candles from Jul 15, matured at the prior cutoff Sat Aug 1, 2026, 16:00 UTC under the same engine, the same FH gate and the same hit rule as August -- 19,541 directional calls against 19,383 in the month. Month-over-month deltas are a step between two windows of different length.",
"Two cutoffs live in this issue. The month is frozen at Mon Sep 1, 2026, 16:00 UTC; the four weekly blocks are frozen at their own published cutoffs (W1 Aug 3-9, W2 Aug 10-16, W3 Aug 17-23, W4 Aug 24-30). A forecast still pending at its week's cutoff is immature in the weekly pack and mature in the month pull, so the month does not equal the sum of the weeks (19,383 vs 17,418 directional, plus 1,965 on the 3 remainder days) -- that gap is arithmetic, not a data problem.",
"Observations inside one window are not independent, and the 95% Wilson CIs shown throughout are descriptive, not inferential. Ranks are ordinal: a 0.3pp gap and a 6pp gap both read as one rank position, so the rank-stability table prints the hit rate next to every rank.",
"The reversal detector remains v1 and BTC/ETH-only, on price series reconstructed from trade entry prices; 9 events in this window still cannot characterise detector performance. Cross-TF and cross-FH disagreement cells are small (n=91, 23, 122, 32); cells under N=10 are insufficient and never used to rank models.",
"Model lines in this window: claude-fable-5, claude-opus-5, deepseek-v4-pro, gemini-3.1-pro, gpt-5.6-sol, grok-4.6 (spliced), qwen-3.8-max (spliced). Series density and lineage notes (monthly #1): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so across this 31-day window daily coverage is PARTIAL as measured -- the 1w series has slots on 13 of 31 days and the 1M series on 10 of 31 days; both sit outside this report's FH gate (1h/4h/1d) and appear only in the exclusions counter (1w 906, 1M 698). (2) 2 model lines are lineage splices inside this window: grok-4.6 (incl. 4.5-era, Aug 1-24); qwen-3.8-max (incl. 3.7-era, Aug 1-5). (3) Every per-model aggregate in this issue sees the merged head id; the raw id is kept in the pack, and 5,390 rows were remapped inside the month against 19,532 in the prior window.",
"Market-state row is computed on a single-exchange (binance) daily candle series, as in the weekly series after the audit that found the raw table mixes two exchanges. The prior-month block is PARTIAL: audited daily candles start 2026-07-15, so it covers 17 days (Jul 15-31), and the TOP5 volume figure compares a 31-day sum with a 17-day sum -- a level difference, not a like-for-like change.",
"Research-to-date counter: directional forecasts resolved inside the FH gate (1h/4h/1d) since Jul 11, counted at the issue cutoff (Mon Sep 1, 2026, 16:00 UTC) -- the D2 definition pinned in the weekly series; this issue prints 39,073. The pack carries no prior-cutoff pin for a monthly window (the prior-cutoff pin is null by construction), so the control this issue is the weekly reproduction: the W4 block of this pack reproduces the published weekly #4 on 7 of 7 checks. Counter deltas against pre-wave-3 issues remain definitional."
],
"notes": {
"series_density_and_lineage_monthly1": "Series density and lineage notes (monthly #1): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so across this 31-day window daily coverage is PARTIAL as measured -- the 1w series has slots on 13 of 31 days and the 1M series on 10 of 31 days; both sit outside this report's FH gate (1h/4h/1d) and appear only in the exclusions counter (1w 906, 1M 698). (2) 2 model lines are lineage splices inside this window: grok-4.6 (incl. 4.5-era, Aug 1-24); qwen-3.8-max (incl. 3.7-era, Aug 1-5). (3) Every per-model aggregate in this issue sees the merged head id; the raw id is kept in the pack, and 5,390 rows were remapped inside the month against 19,532 in the prior window.",
"grok_era": {
"ids_in_window": [
"grok-4.5",
"grok-4.6"
],
"n_grok45": 4520,
"n_grok46": 1570,
"n_grok45_rows": 4520,
"n_grok46_rows": 1570,
"first_grok46_slot": "2026-08-24T10:01:00+00:00",
"last_grok45_slot": "2026-08-24T09:01:00+00:00",
"first_grok45_slot": "2026-08-01T00:01:00+00:00",
"flip_at": "2026-08-24T09:22:00+00:00",
"flip_inside_window": true,
"prev_window": {
"n_grok45_rows": 6608,
"n_grok46_rows": 0
},
"merged_model_id": "grok-4.6",
"merged_label": "grok-4.6 (incl. 4.5-era, Aug 1-24)",
"lineage_ids": [
"grok-4.5",
"grok-4.6"
],
"lineage_source": "benchmarks.config.lineage_ids(head) for each of the 7 heads + MODEL_SUCCESSION[claude-opus-5=('claude-opus-4.8',), grok-4.6=('grok-4.5',), qwen-3.8-max=('qwen-3.7-max',)]",
"lineage_warnings": [],
"rows_remapped_a_plus_b": 11128,
"note": "window MONTH [2026-08-01T00:00:00+00:00, 2026-09-01T00:00:00+00:00): grok-4.5 rows 4520, grok-4.6 rows 1570; flip 2026-08-24T09:22:00+00:00 is inside this window. All per-model aggregates use the lineage splice grok-4.5 -> grok-4.6 (one row, labelled 'grok-4.6 (incl. 4.5-era, Aug 1-24)'). See lineage_era for the same facts across all 7 heads.",
"cells_with_two_grok_rows": 0
},
"model_ids_line": [
"claude-fable-5",
"claude-opus-5",
"deepseek-v4-pro",
"gemini-3.1-pro",
"gpt-5.6-sol",
"grok-4.6",
"qwen-3.8-max"
],
"model_roster": {
"current": [
"claude-fable-5",
"claude-opus-5",
"deepseek-v4-pro",
"gemini-3.1-pro",
"gpt-5.6-sol",
"grok-4.6",
"qwen-3.8-max"
],
"current_count": 7,
"current_raw_ids_in_window": [
"claude-fable-5",
"claude-opus-5",
"deepseek-v4-pro",
"gemini-3.1-pro",
"gpt-5.6-sol",
"grok-4.5",
"grok-4.6",
"qwen-3.7-max",
"qwen-3.8-max"
],
"archived_legacy": [
"grok-4.5",
"qwen-3.7-max",
"claude-opus-4.8"
],
"archived_legacy_count": 3,
"archived_legacy_detail": [
{
"model": "grok-4.5",
"n_rows_since": 11128,
"first_slot": "2026-07-15T18:01:00+00:00",
"last_slot": "2026-08-24T09:01:00+00:00"
},
{
"model": "qwen-3.7-max",
"n_rows_since": 7479,
"first_slot": "2026-07-15T18:01:00+00:00",
"last_slot": "2026-08-05T09:01:00+00:00"
},
{
"model": "claude-opus-4.8",
"n_rows_since": 6315,
"first_slot": "2026-07-15T18:01:00+00:00",
"last_slot": "2026-07-30T08:01:00+00:00"
}
],
"archived_excluding_lineage_merged": [],
"tracked_total": 10,
"canon_expected": {
"current": 7,
"archived_legacy": 4,
"tracked_total": 11
},
"matches_canon_11_7_4": false,
"roster_rule_w213": "7 models tracked (current line-up; earlier versions folded into their successors' lineage)",
"canon_expected_w213": {
"current": 7
},
"heads_w213": [
"claude-fable-5",
"claude-opus-5",
"deepseek-v4-pro",
"gemini-3.1-pro",
"gpt-5.6-sol",
"grok-4.6",
"qwen-3.8-max"
],
"matches_canon_7_current": true,
"heads_missing_in_window": [],
"heads_unexpected_in_window": [],
"roster_since": "2026-07-11T00:00:00+00:00",
"note": "current = merged-lineage model ids emitting inside the window (legacy ids are spliced into their successor); archived legacy = raw ids seen since 2026-07-11 that no longer emit in the window. Models retired before 2026-07-11 are not visible to this query. The canon checks are DESCRIPTIVE: if the data says otherwise, the data wins and is printed."
},
"series_density": {
"1d": {
"days_with_slots": 31,
"expected_days": 31,
"full_daily_coverage": true,
"in_fh_gate": true,
"n_slots": 31,
"n_rows": 2170,
"days": [
"2026-08-01",
"2026-08-02",
"2026-08-03",
"2026-08-04",
"2026-08-05",
"2026-08-06",
"2026-08-07",
"2026-08-08",
"2026-08-09",
"2026-08-10",
"2026-08-11",
"2026-08-12",
"2026-08-13",
"2026-08-14",
"2026-08-15",
"2026-08-16",
"2026-08-17",
"2026-08-18",
"2026-08-19",
"2026-08-20",
"2026-08-21",
"2026-08-22",
"2026-08-23",
"2026-08-24",
"2026-08-25",
"2026-08-26",
"2026-08-27",
"2026-08-28",
"2026-08-29",
"2026-08-30",
"2026-08-31"
],
"missing_days": []
},
"1h": {
"days_with_slots": 31,
"expected_days": 31,
"full_daily_coverage": true,
"in_fh_gate": true,
"n_slots": 741,
"n_rows": 25935,
"days": [
"2026-08-01",
"2026-08-02",
"2026-08-03",
"2026-08-04",
"2026-08-05",
"2026-08-06",
"2026-08-07",
"2026-08-08",
"2026-08-09",
"2026-08-10",
"2026-08-11",
"2026-08-12",
"2026-08-13",
"2026-08-14",
"2026-08-15",
"2026-08-16",
"2026-08-17",
"2026-08-18",
"2026-08-19",
"2026-08-20",
"2026-08-21",
"2026-08-22",
"2026-08-23",
"2026-08-24",
"2026-08-25",
"2026-08-26",
"2026-08-27",
"2026-08-28",
"2026-08-29",
"2026-08-30",
"2026-08-31"
],
"missing_days": []
},
"1m": {
"days_with_slots": 10,
"expected_days": 31,
"full_daily_coverage": false,
"in_fh_gate": false,
"n_slots": 10,
"n_rows": 700,
"days": [
"2026-08-01",
"2026-08-23",
"2026-08-24",
"2026-08-25",
"2026-08-26",
"2026-08-27",
"2026-08-28",
"2026-08-29",
"2026-08-30",
"2026-08-31"
],
"missing_days": [
"2026-08-02",
"2026-08-03",
"2026-08-04",
"2026-08-05",
"2026-08-06",
"2026-08-07",
"2026-08-08",
"2026-08-09",
"2026-08-10",
"2026-08-11",
"2026-08-12",
"2026-08-13",
"2026-08-14",
"2026-08-15",
"2026-08-16",
"2026-08-17",
"2026-08-18",
"2026-08-19",
"2026-08-20",
"2026-08-21",
"2026-08-22"
]
},
"1w": {
"days_with_slots": 13,
"expected_days": 31,
"full_daily_coverage": false,
"in_fh_gate": false,
"n_slots": 13,
"n_rows": 910,
"days": [
"2026-08-03",
"2026-08-10",
"2026-08-17",
"2026-08-22",
"2026-08-23",
"2026-08-24",
"2026-08-25",
"2026-08-26",
"2026-08-27",
"2026-08-28",
"2026-08-29",
"2026-08-30",
"2026-08-31"
],
"missing_days": [
"2026-08-01",
"2026-08-02",
"2026-08-04",
"2026-08-05",
"2026-08-06",
"2026-08-07",
"2026-08-08",
"2026-08-09",
"2026-08-11",
"2026-08-12",
"2026-08-13",
"2026-08-14",
"2026-08-15",
"2026-08-16",
"2026-08-18",
"2026-08-19",
"2026-08-20",
"2026-08-21"
]
},
"4h": {
"days_with_slots": 31,
"expected_days": 31,
"full_daily_coverage": true,
"in_fh_gate": true,
"n_slots": 185,
"n_rows": 12939,
"days": [
"2026-08-01",
"2026-08-02",
"2026-08-03",
"2026-08-04",
"2026-08-05",
"2026-08-06",
"2026-08-07",
"2026-08-08",
"2026-08-09",
"2026-08-10",
"2026-08-11",
"2026-08-12",
"2026-08-13",
"2026-08-14",
"2026-08-15",
"2026-08-16",
"2026-08-17",
"2026-08-18",
"2026-08-19",
"2026-08-20",
"2026-08-21",
"2026-08-22",
"2026-08-23",
"2026-08-24",
"2026-08-25",
"2026-08-26",
"2026-08-27",
"2026-08-28",
"2026-08-29",
"2026-08-30",
"2026-08-31"
],
"missing_days": []
}
},
"month_over_month_note": "Month-over-month columns compare back-to-back windows: Jul 11-31 (partial) vs Aug 1-31 (this issue). \"Was\" values are the pack's own prior-window block -- window A of the same pull, same engine, same FH gate and same hit rule, matured at the prior cutoff Sat Aug 1, 2026, 16:00 UTC. The prior month is PARTIAL: forecasts run from Jul 11 and audited candles from Jul 15, so it holds 19,541 directional calls against 19,383 in August. Deltas are computed on unrounded rates.",
"research_to_date_pin": "Research-to-date counter: directional forecasts resolved inside the FH gate (1h/4h/1d) since Jul 11, counted at the issue cutoff (Mon Sep 1, 2026, 16:00 UTC) -- the D2 definition pinned in the weekly series; this issue prints 39,073. The pack carries no prior-cutoff pin for a monthly window (the prior-cutoff pin is null by construction), so the control this issue is the weekly reproduction: the W4 block of this pack reproduces the published weekly #4 on 7 of 7 checks. Counter deltas against pre-wave-3 issues remain definitional.",
"market_state_audit": "Market-state row is computed on a single-exchange (binance) daily candle series, as in the weekly series after the audit that found the raw table mixes two exchanges. The prior-month block is PARTIAL: audited daily candles start 2026-07-15, so it covers 17 days (Jul 15-31), and the TOP5 volume figure compares a 31-day sum with a 17-day sum -- a level difference, not a like-for-like change.",
"engine": "Engine 1.1 has powered the sandbox since Aug 18, i.e. inside this window; no cross-engine PnL comparisons are claimed.",
"report_template": "PDF built with the canonical mm_report.py template module; preview card with report_preview.render_preview",
"lineage_era": {
"window_key": "MONTH",
"heads": [
"claude-fable-5",
"claude-opus-5",
"deepseek-v4-pro",
"gemini-3.1-pro",
"gpt-5.6-sol",
"grok-4.6",
"qwen-3.8-max"
],
"lineage_map": {
"claude-opus-4.8": "claude-opus-5",
"grok-4.5": "grok-4.6",
"qwen-3.7-max": "qwen-3.8-max"
},
"legacy_by_head": {
"claude-fable-5": [],
"claude-opus-5": [
"claude-opus-4.8"
],
"deepseek-v4-pro": [],
"gemini-3.1-pro": [],
"gpt-5.6-sol": [],
"grok-4.6": [
"grok-4.5"
],
"qwen-3.8-max": [
"qwen-3.7-max"
]
},
"lineage_source": "benchmarks.config.lineage_ids(head) for each of the 7 heads + MODEL_SUCCESSION[claude-opus-5=('claude-opus-4.8',), grok-4.6=('grok-4.5',), qwen-3.8-max=('qwen-3.7-max',)]",
"lineage_resolved_heads": [
"claude-fable-5",
"claude-opus-5",
"deepseek-v4-pro",
"gemini-3.1-pro",
"gpt-5.6-sol",
"grok-4.6",
"qwen-3.8-max"
],
"lineage_warnings": [],
"per_head": {
"claude-fable-5": {
"legacy_ids": [],
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"n_rows_remapped_prev_window": {},
"by_legacy_id": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-01T00:01:00+00:00",
"last_successor_slot": "2026-08-31T23:01:00+00:00",
"n_rows_successor": 6095,
"spliced_in_window": false,
"label": "claude-fable-5"
},
"claude-opus-5": {
"legacy_ids": [
"claude-opus-4.8"
],
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {
"claude-opus-4.8": 0
},
"n_rows_remapped_prev_window": {
"claude-opus-4.8": 6315
},
"by_legacy_id": {
"claude-opus-4.8": {
"n_rows_remapped": {
"MONTH": 0,
"prev_window": 6315
},
"first_slot": null,
"last_slot": null,
"first_slot_prev_window": "2026-07-15T18:01:00+00:00",
"last_slot_prev_window": "2026-07-30T08:01:00+00:00"
}
},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-01T00:01:00+00:00",
"last_successor_slot": "2026-08-31T23:01:00+00:00",
"n_rows_successor": 6095,
"spliced_in_window": false,
"label": "claude-opus-5"
},
"deepseek-v4-pro": {
"legacy_ids": [],
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"n_rows_remapped_prev_window": {},
"by_legacy_id": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-01T00:01:00+00:00",
"last_successor_slot": "2026-08-31T23:01:00+00:00",
"n_rows_successor": 6095,
"spliced_in_window": false,
"label": "deepseek-v4-pro"
},
"gemini-3.1-pro": {
"legacy_ids": [],
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"n_rows_remapped_prev_window": {},
"by_legacy_id": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-01T00:01:00+00:00",
"last_successor_slot": "2026-08-31T23:01:00+00:00",
"n_rows_successor": 6094,
"spliced_in_window": false,
"label": "gemini-3.1-pro"
},
"gpt-5.6-sol": {
"legacy_ids": [],
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"n_rows_remapped_prev_window": {},
"by_legacy_id": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-01T00:01:00+00:00",
"last_successor_slot": "2026-08-31T23:01:00+00:00",
"n_rows_successor": 6095,
"spliced_in_window": false,
"label": "gpt-5.6-sol"
},
"grok-4.6": {
"legacy_ids": [
"grok-4.5"
],
"legacy_ids_seen_in_window": [
"grok-4.5"
],
"n_rows_remapped": {
"grok-4.5": 4520
},
"n_rows_remapped_prev_window": {
"grok-4.5": 6608
},
"by_legacy_id": {
"grok-4.5": {
"n_rows_remapped": {
"MONTH": 4520,
"prev_window": 6608
},
"first_slot": "2026-08-01T00:01:00+00:00",
"last_slot": "2026-08-24T09:01:00+00:00",
"first_slot_prev_window": "2026-07-15T18:01:00+00:00",
"last_slot_prev_window": "2026-07-31T23:01:00+00:00"
}
},
"first_legacy_slot": "2026-08-01T00:01:00+00:00",
"last_legacy_slot": "2026-08-24T09:01:00+00:00",
"first_successor_slot": "2026-08-24T10:01:00+00:00",
"last_successor_slot": "2026-08-31T23:01:00+00:00",
"n_rows_successor": 1570,
"spliced_in_window": true,
"label": "grok-4.6 (incl. 4.5-era, Aug 1-24)"
},
"qwen-3.8-max": {
"legacy_ids": [
"qwen-3.7-max"
],
"legacy_ids_seen_in_window": [
"qwen-3.7-max"
],
"n_rows_remapped": {
"qwen-3.7-max": 870
},
"n_rows_remapped_prev_window": {
"qwen-3.7-max": 6609
},
"by_legacy_id": {
"qwen-3.7-max": {
"n_rows_remapped": {
"MONTH": 870,
"prev_window": 6609
},
"first_slot": "2026-08-01T00:01:00+00:00",
"last_slot": "2026-08-05T09:01:00+00:00",
"first_slot_prev_window": "2026-07-15T18:01:00+00:00",
"last_slot_prev_window": "2026-07-31T23:01:00+00:00"
}
},
"first_legacy_slot": "2026-08-01T00:01:00+00:00",
"last_legacy_slot": "2026-08-05T09:01:00+00:00",
"first_successor_slot": "2026-08-05T10:01:00+00:00",
"last_successor_slot": "2026-08-31T23:01:00+00:00",
"n_rows_successor": 5220,
"spliced_in_window": true,
"label": "qwen-3.8-max (incl. 3.7-era, Aug 1-5)"
}
},
"labels": {
"claude-fable-5": "claude-fable-5",
"claude-opus-5": "claude-opus-5",
"deepseek-v4-pro": "deepseek-v4-pro",
"gemini-3.1-pro": "gemini-3.1-pro",
"gpt-5.6-sol": "gpt-5.6-sol",
"grok-4.6": "grok-4.6 (incl. 4.5-era, Aug 1-24)",
"qwen-3.8-max": "qwen-3.8-max (incl. 3.7-era, Aug 1-5)"
},
"rows_remapped_window": 5390,
"rows_remapped_prev_window": 19532,
"note": "Only the 7 current models are tracked; earlier versions are folded into their successors' lineage. Every per-model aggregate in this pack sees the merged head id; the raw id survives in model_raw. Labels and era spans are generated from the pulled rows, not hardcoded.",
"cells_with_two_rows_per_head": {
"claude-fable-5": 0,
"claude-opus-5": 0,
"deepseek-v4-pro": 0,
"gemini-3.1-pro": 0,
"gpt-5.6-sol": 0,
"grok-4.6": 0,
"qwen-3.8-max": 0
}
},
"frozen_cutoffs": "Two cutoffs live in this issue. The month is frozen at Mon Sep 1, 2026, 16:00 UTC; the four weekly blocks are frozen at their own published cutoffs (W1 Aug 3-9, W2 Aug 10-16, W3 Aug 17-23, W4 Aug 24-30). A forecast still pending at its week's cutoff is immature in the weekly pack and mature in the month pull, so the month does not equal the sum of the weeks (19,383 vs 17,418 directional, plus 1,965 on the 3 remainder days) -- that gap is arithmetic, not a data problem.",
"partial_prior_window": "The prior window is a PARTIAL month: forecasts run only from Jul 11 and the audited daily candles only from Jul 15, so every \"prior\" column, the gray series of the page-1 chart and the market-check A column describe Jul 11-31 (partial), not a full July. It is window A of the same pull, slots 2026-07-01 to 2026-08-01, forecasts counted from Jul 11 (first slot actually seen 2026-07-15 18:01 UTC) and audited candles from Jul 15, matured at the prior cutoff Sat Aug 1, 2026, 16:00 UTC under the same engine, the same FH gate and the same hit rule as August -- 19,541 directional calls against 19,383 in the month. Month-over-month deltas are a step between two windows of different length."
},
"living_series_note": "**Issue #1.** Monthly Model Watch is a living monthly comparison; each issue appends one more calendar month of leaderboard, asset-league, rank-stability and regime data. This first issue sets the baseline: claude-opus-5 at the top (47.8%), 6 of 9 qualifying turns found a caller, 0 of 5 tickers above 51%, 3 distinct model lines leading the four weeks and a calm-vs-volatile field difference of +5.7pp. 2 model lines are lineage splices this month (grok-4.6 (incl. 4.5-era, Aug 1-24); qwen-3.8-max (incl. 3.7-era, Aug 1-5)). Engine 1.1 has powered the sandbox since Aug 18, i.e. inside this window; no cross-engine PnL comparisons are claimed.",
"testing_next": [
"Monthly #2 (September): the same three series over Sep 1-30, cut on Oct 1 plus the maturity lag, so the first month-over-month comparison runs against a FULL prior month instead of a partial one.",
"Monthly Config Watch #1: the same August window through the config search engine (w200), published as the fourth monthly report of this issue.",
"Quarterly Stability Index: the next identical-prompt run lands around Oct 8 and is the first cross-quarter point on model stability."
],
"related_research": [
{
"title": "Monthly Consensus Watch #1",
"url": "https://marketmania.ai/research/reports/consensus-watch-monthly-2026-08.pdf"
},
{
"title": "Monthly Calibration #1",
"url": "https://marketmania.ai/research/reports/calibration-monthly-2026-08.pdf"
},
{
"title": "Weekly Model Watch #4",
"url": "https://marketmania.ai/research/reports/model-watch-2026-08-24.pdf"
}
],
"related_research_note": "The three monthly reports publish together as one issue each month; each links straight to the others' PDF and to the last weekly issue of the same series. Direct links are the posting rule from wave 2 on.",
"research_to_date": {
"this_report": {
"scored_observations": 19383
},
"platform": {
"as_of_cutoff": "2026-09-01",
"resolved_forecasts": 39073,
"resolved_forecasts_definition": "directional forecasts resolved inside the FH gate (1h/4h/1d) since Jul 11, at the issue cutoff",
"resolved_forecasts_since": "2026-07-11",
"models_tracked": 7,
"models_tracked_detail": "7 models tracked (current line-up; earlier versions folded into their successors' lineage)",
"assets": 5,
"forecast_horizons": 5,
"cadence": "hourly",
"published_research_reports": 21
},
"source": "monthly_metrics_2026-08.json",
"control_reproduces_wave3_pin": null,
"pin_note": "Research-to-date counter: directional forecasts resolved inside the FH gate (1h/4h/1d) since Jul 11, counted at the issue cutoff (Mon Sep 1, 2026, 16:00 UTC) -- the D2 definition pinned in the weekly series; this issue prints 39,073. The pack carries no prior-cutoff pin for a monthly window (the prior-cutoff pin is null by construction), so the control this issue is the weekly reproduction: the W4 block of this pack reproduces the published weekly #4 on 7 of 7 checks. Counter deltas against pre-wave-3 issues remain definitional.",
"control_w4_reproduces_wave4": {
"pins_source": "weekly_metrics_2026-08-24.json (the published wave-4 pack)",
"note": "W4 of this run is the wave-4 weekly window with the wave-4 frozen cutoff, so every pin must reproduce exactly. A mismatch means the window or the cutoff moved -- non-fatal here, but the monthly numbers must not be published until it is explained.",
"checks": {
"counters.mature_directional": {
"pin": 4576,
"got": 4576,
"match": true,
"tolerance": 0
},
"calibration.field.hit_rate": {
"pin": 0.4294,
"got": 0.4294,
"match": true,
"tolerance": 5e-05
},
"calibration.field.gap_pp": {
"pin": 19.6,
"got": 19.6,
"match": true,
"tolerance": 0.05
},
"consensus.loo_pooled.lift_pp": {
"pin": -6.0,
"got": -6.0,
"match": true,
"tolerance": 0.05
},
"model_watch.leaderboard.rows[0].model": {
"pin": "deepseek-v4-pro",
"got": "deepseek-v4-pro",
"match": true,
"tolerance": 0
},
"model_watch.leaderboard.rows[0].hit_rate": {
"pin": 0.4458,
"got": 0.4458,
"match": true,
"tolerance": 5e-05
},
"research_to_date.canonical_value_at_cutoff": {
"pin": 38385,
"got": 38385,
"match": true,
"tolerance": 0
}
},
"all_match": true,
"n_checks": 7,
"n_match": 7
}
},
"citation": {
"bibtex_key": "mm_modelwatch_monthly_2026m08",
"title": "Monthly Model Watch #1: monthly leaderboard, asset league, rank stability and regime split, Aug 1-31 2026",
"author": "MarketMania Research",
"year": 2026,
"month": "September",
"day": 4,
"url": "https://marketmania.ai/research/reports/model-watch-monthly-2026-08.pdf",
"note": "Methodology v1.1; window Aug 1-31, 2026 UTC; source monthly_metrics_2026-08.json"
},
"site_entry": {
"slug": "model-watch-monthly-2026-08",
"series": "monthly",
"seriesLabel": "Monthly · Model Watch",
"date": "September 4, 2026",
"title": "Monthly Model Watch #1",
"summary": "19,383 directional calls over one calendar month, three questions the weekly series cannot answer: which coin the field reads best over a month, how far a weekly rank moves inside one month, and how accuracy differs between the calm and the volatile weeks. No monthly title — claude-opus-5 led at 47.8% (+2.9pp vs the partial July) against gemini-3.1-pro at 47.6%, a gap of 0.2pp, while 3 different model lines held the weekly top spot inside the same month. BNB was the most readable ticker at 48.1% and ETH the hardest at 42.9%, with 0 of 5 assets above 51 percent. Calm weeks hit 43.1% against 48.8% in the volatile ones (+5.7pp). Reversals: 6 of 9 qualifying turns found a caller. Field accuracy moved 45.0% -> 46.3% (+1.4pp) with 5 of 7 models improving.",
"stats": [
"19,383 directional calls",
"No monthly title",
"field +1.4pp m/m"
],
"manifest_key_finding": "Field accuracy moved 45.0% -> 46.3% (+1.4pp) against the partial July with 5 of 7 models improving; claude-opus-5 led the month at 47.8%, 3 different lines led the four weeks inside it, and no monthly title was awarded.",
"files": {
"pdf": "/research/reports/model-watch-monthly-2026-08.pdf",
"md": "/research/reports/model-watch-monthly-2026-08.md",
"json": "/research/reports/model-watch-monthly-2026-08.json"
}
},
"social": {
"telegram": {
"photo_caption_html": "📊 Monthly Model Watch #1 — monthly series (window Aug 1–31)\n\nWho led, what was readable, who saw the turn? 19,383 directional calls, 7 lines, one month:\n• No monthly title — claude-opus-5 leads at 47.8% (+2.9pp m/m) against gemini-3.1-pro at 47.6%, a 0.2pp gap\n• Rank stability: 3 different lines topped the four weeks inside the month\n• Asset league: BNB most readable (48.1%); ETH hardest at 42.9% — 0 of 5 above 51%\n• Calm vs volatile weeks: field 43.1% vs 48.8% (+5.7pp)\n• Reversals: 6 of 9 qualifying turns found a caller\n• Market check: field 45.0% -> 46.3% (+1.4pp), 5 of 7 improved\n\nNote: prior window = PARTIAL July (forecasts since Jul 11); two lines are lineage splices\n\n📄 Full report (PDF) · all research\n\n#cryptotrading #LLM #AI #crypto #trading #models #research #Monthly",
"document_caption_html": "📄 Monthly Model Watch #1 — full report (PDF).\nWeb copy: model-watch-monthly-2026-08.pdf · machine-readable: JSON · all research\n\n#cryptotrading #LLM #AI #crypto #trading #models #research #Monthly",
"caption_len": 959,
"document_caption_len": 415,
"limit": 1024
},
"x": {
"main": "Monthly Model Watch #1 is out.\n\n19,383 directional LLM calls over August: claude-opus-5 led at 47.8%, but 3 different lines topped the four weeks inside the month. BNB was the most readable coin.\n\nFull report: https://marketmania.ai/research/reports/model-watch-monthly-2026-08.pdf\n\n#AI #Crypto #Research #LLM",
"main_tco_len": 261,
"reply": "Hit-rate, partial July -> August:\nopus-5: 44.9 -> 47.8\ngemini-3.1: 45.1 -> 47.6\nfable-5: 44.5 -> 46.7\ngpt-5.6: 44.3 -> 45.9\nqwen-3.8: 45.7 -> 45.6\ndeepseek: 45.1 -> 45.5\ngrok-4.6: 45.3 -> 45.3\nField: 45.0 -> 46.3. Calm 43.1% vs volatile 48.8%.\nData: https://marketmania.ai/research/reports/model-watch-monthly-2026-08.json",
"reply_tco_len": 273,
"limit_tco": 280,
"replies_max": 1
}
},
"monthly_window": {
"start": "2026-08-01T00:00:00+00:00",
"end": "2026-09-01T00:00:00+00:00",
"text": "Aug 1-31, 2026 UTC",
"cutoff": "2026-09-01T16:00:00+00:00",
"cutoff_text": "Mon Sep 1, 2026, 16:00 UTC",
"days": 31,
"label": "Aug 1-31"
},
"prior_window": {
"start": "2026-07-01T00:00:00+00:00",
"end": "2026-08-01T00:00:00+00:00",
"text": "Jul 11-31, 2026 (partial month; forecasts since Jul 11)",
"printed_as": "Jul 11-31 (partial)",
"cutoff_text": "Sat Aug 1, 2026, 16:00 UTC",
"partial": true,
"note": "July is partial: forecasts since 2026-07-11",
"applicable": true,
"not_applicable_reason": null,
"source": "month.prior_window -- window A of the same pull, matured at the prior cutoff with the same gate, maturity and hit rule",
"effective_start": "2026-07-15T18:01:00+00:00",
"counters": {
"forecasts_total": 46285,
"ok_in_gate": 42134,
"mature": 41985,
"mature_directional": 19541,
"mature_sideways": 22444
},
"definitions": {
"maturity": "horizon expired AND trade closed by the PRIOR cutoff (the same rule the current window uses at its own cutoff)",
"hit": "direction: exit tp1/tp2 -> hit, sl -> miss, expiry -> sign of gross pnl",
"fh_gate": [
"1h",
"4h",
"1d"
],
"min_n": 10,
"lineage": "rows spliced by the generalised 7-head lineage map before any aggregate",
"note": "identical definitions to the current window; only the window and the cutoff differ"
}
},
"weeks_index": {
"W1": {
"label": "Aug 3-9",
"issue": 1,
"published_slug_suffix": [
"2026-08-03T00:00:00Z",
"2026-08-10T00:00:00Z"
],
"bounds": [
"2026-08-03T00:00:00Z",
"2026-08-10T00:00:00Z"
],
"regime": "calm"
},
"W2": {
"label": "Aug 10-16",
"issue": 2,
"published_slug_suffix": [
"2026-08-10T00:00:00Z",
"2026-08-17T00:00:00Z"
],
"bounds": [
"2026-08-10T00:00:00Z",
"2026-08-17T00:00:00Z"
],
"regime": "calm"
},
"W3": {
"label": "Aug 17-23",
"issue": 3,
"published_slug_suffix": [
"2026-08-17T00:00:00Z",
"2026-08-24T00:00:00Z"
],
"bounds": [
"2026-08-17T00:00:00Z",
"2026-08-24T00:00:00Z"
],
"regime": "volatile"
},
"W4": {
"label": "Aug 24-30",
"issue": 4,
"published_slug_suffix": [
"2026-08-24T00:00:00Z",
"2026-08-31T00:00:00Z"
],
"bounds": [
"2026-08-24T00:00:00Z",
"2026-08-31T00:00:00Z"
],
"regime": "volatile"
}
},
"roster_rule": "7 models tracked (current line-up; earlier versions folded into their successors' lineage)",
"lineage_labels": {
"labels": {
"claude-fable-5": "claude-fable-5",
"claude-opus-5": "claude-opus-5",
"deepseek-v4-pro": "deepseek-v4-pro",
"gemini-3.1-pro": "gemini-3.1-pro",
"gpt-5.6-sol": "gpt-5.6-sol",
"grok-4.6": "grok-4.6 (incl. 4.5-era, Aug 1-24)",
"qwen-3.8-max": "qwen-3.8-max (incl. 3.7-era, Aug 1-5)"
},
"spliced_in_window": [
"grok-4.6",
"qwen-3.8-max"
],
"cell_form": {
"grok-4.6": "grok-4.6 (spliced)",
"qwen-3.8-max": "qwen-3.8-max (spliced)"
},
"families": [
"grok",
"qwen"
]
},
"controls": {
"w4_reproduces_wave4": {
"pins_source": "weekly_metrics_2026-08-24.json (the published wave-4 pack)",
"note": "W4 of this run is the wave-4 weekly window with the wave-4 frozen cutoff, so every pin must reproduce exactly. A mismatch means the window or the cutoff moved -- non-fatal here, but the monthly numbers must not be published until it is explained.",
"checks": {
"counters.mature_directional": {
"pin": 4576,
"got": 4576,
"match": true,
"tolerance": 0
},
"calibration.field.hit_rate": {
"pin": 0.4294,
"got": 0.4294,
"match": true,
"tolerance": 5e-05
},
"calibration.field.gap_pp": {
"pin": 19.6,
"got": 19.6,
"match": true,
"tolerance": 0.05
},
"consensus.loo_pooled.lift_pp": {
"pin": -6.0,
"got": -6.0,
"match": true,
"tolerance": 0.05
},
"model_watch.leaderboard.rows[0].model": {
"pin": "deepseek-v4-pro",
"got": "deepseek-v4-pro",
"match": true,
"tolerance": 0
},
"model_watch.leaderboard.rows[0].hit_rate": {
"pin": 0.4458,
"got": 0.4458,
"match": true,
"tolerance": 5e-05
},
"research_to_date.canonical_value_at_cutoff": {
"pin": 38385,
"got": 38385,
"match": true,
"tolerance": 0
}
},
"all_match": true,
"n_checks": 7,
"n_match": 7
},
"month_vs_weeks": {
"month": 19383,
"sum_weeks": 17418,
"per_week": {
"W1": 4042,
"W2": 3670,
"W3": 5130,
"W4": 4576
},
"remainder_days": [
"2026-08-01",
"2026-08-02",
"2026-08-31"
],
"remainder_days_n": 3,
"remainder_mature_directional_month_pull": 1965,
"remainder_by_day": {
"2026-08-02": 756,
"2026-08-01": 521,
"2026-08-31": 688
},
"sum_weeks_plus_remainder": 19383,
"month_minus_sum_weeks_plus_remainder": 0,
"month_pull_by_week": {
"W1": 4042,
"W2": 3670,
"W3": 5130,
"W4": 4576
},
"note": "These WILL differ, and the difference is expected: each weekly pack is computed at its own frozen cutoff (week_end + 16h), while the MONTH pack is computed at 2026-09-01T16:00Z. A forecast still pending at its week's cutoff (trade not yet closed) is immature in the weekly pack and mature in the MONTH pack, so month >= sum_weeks + remainder. remainder_days_n counts the calendar days of August outside the four Mon-Sun weeks (Aug 1, Aug 2, Aug 31). month_pull_by_week is the same month pull split by slot week at the MONTH cutoff -- compare THAT with per_week to see the cutoff effect alone."
},
"lineage_splice_counts": {
"MONTH": {
"claude-opus-4.8": 0,
"grok-4.5": 4520,
"qwen-3.7-max": 870
},
"W1": {
"claude-opus-4.8": 0,
"grok-4.5": 1310,
"qwen-3.7-max": 480
},
"W2": {
"claude-opus-4.8": 0,
"grok-4.5": 1340,
"qwen-3.7-max": 0
},
"W3": {
"claude-opus-4.8": 0,
"grok-4.5": 1370,
"qwen-3.7-max": 0
},
"W4": {
"claude-opus-4.8": 0,
"grok-4.5": 110,
"qwen-3.7-max": 0
}
},
"lineage_splice_detail": {
"MONTH": {
"total_window": 5390,
"total_prev_window": 19532,
"labels": {
"claude-fable-5": "claude-fable-5",
"claude-opus-5": "claude-opus-5",
"deepseek-v4-pro": "deepseek-v4-pro",
"gemini-3.1-pro": "gemini-3.1-pro",
"gpt-5.6-sol": "gpt-5.6-sol",
"grok-4.6": "grok-4.6 (incl. 4.5-era, Aug 1-24)",
"qwen-3.8-max": "qwen-3.8-max (incl. 3.7-era, Aug 1-5)"
},
"per_head": {
"claude-fable-5": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-01T00:01:00+00:00"
},
"claude-opus-5": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {
"claude-opus-4.8": 0
},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-01T00:01:00+00:00"
},
"deepseek-v4-pro": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-01T00:01:00+00:00"
},
"gemini-3.1-pro": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-01T00:01:00+00:00"
},
"gpt-5.6-sol": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-01T00:01:00+00:00"
},
"grok-4.6": {
"legacy_ids_seen_in_window": [
"grok-4.5"
],
"n_rows_remapped": {
"grok-4.5": 4520
},
"first_legacy_slot": "2026-08-01T00:01:00+00:00",
"last_legacy_slot": "2026-08-24T09:01:00+00:00",
"first_successor_slot": "2026-08-24T10:01:00+00:00"
},
"qwen-3.8-max": {
"legacy_ids_seen_in_window": [
"qwen-3.7-max"
],
"n_rows_remapped": {
"qwen-3.7-max": 870
},
"first_legacy_slot": "2026-08-01T00:01:00+00:00",
"last_legacy_slot": "2026-08-05T09:01:00+00:00",
"first_successor_slot": "2026-08-05T10:01:00+00:00"
}
}
},
"W1": {
"total_window": 1790,
"total_prev_window": 3373,
"labels": {
"claude-fable-5": "claude-fable-5",
"claude-opus-5": "claude-opus-5",
"deepseek-v4-pro": "deepseek-v4-pro",
"gemini-3.1-pro": "gemini-3.1-pro",
"gpt-5.6-sol": "gpt-5.6-sol",
"grok-4.6": "grok-4.6 (incl. 4.5-era, Aug 3-9)",
"qwen-3.8-max": "qwen-3.8-max (incl. 3.7-era, Aug 3-5)"
},
"per_head": {
"claude-fable-5": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-03T00:01:00+00:00"
},
"claude-opus-5": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {
"claude-opus-4.8": 0
},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-03T00:01:00+00:00"
},
"deepseek-v4-pro": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-03T00:01:00+00:00"
},
"gemini-3.1-pro": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-03T00:01:00+00:00"
},
"gpt-5.6-sol": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-03T00:01:00+00:00"
},
"grok-4.6": {
"legacy_ids_seen_in_window": [
"grok-4.5"
],
"n_rows_remapped": {
"grok-4.5": 1310
},
"first_legacy_slot": "2026-08-03T00:01:00+00:00",
"last_legacy_slot": "2026-08-09T23:01:00+00:00",
"first_successor_slot": null
},
"qwen-3.8-max": {
"legacy_ids_seen_in_window": [
"qwen-3.7-max"
],
"n_rows_remapped": {
"qwen-3.7-max": 480
},
"first_legacy_slot": "2026-08-03T00:01:00+00:00",
"last_legacy_slot": "2026-08-05T09:01:00+00:00",
"first_successor_slot": "2026-08-05T10:01:00+00:00"
}
}
},
"W2": {
"total_window": 1340,
"total_prev_window": 1790,
"labels": {
"claude-fable-5": "claude-fable-5",
"claude-opus-5": "claude-opus-5",
"deepseek-v4-pro": "deepseek-v4-pro",
"gemini-3.1-pro": "gemini-3.1-pro",
"gpt-5.6-sol": "gpt-5.6-sol",
"grok-4.6": "grok-4.6 (incl. 4.5-era, Aug 10-16)",
"qwen-3.8-max": "qwen-3.8-max"
},
"per_head": {
"claude-fable-5": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-10T00:01:00+00:00"
},
"claude-opus-5": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {
"claude-opus-4.8": 0
},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-10T00:01:00+00:00"
},
"deepseek-v4-pro": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-10T00:01:00+00:00"
},
"gemini-3.1-pro": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-10T00:01:00+00:00"
},
"gpt-5.6-sol": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-10T00:01:00+00:00"
},
"grok-4.6": {
"legacy_ids_seen_in_window": [
"grok-4.5"
],
"n_rows_remapped": {
"grok-4.5": 1340
},
"first_legacy_slot": "2026-08-10T00:01:00+00:00",
"last_legacy_slot": "2026-08-16T23:01:00+00:00",
"first_successor_slot": null
},
"qwen-3.8-max": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {
"qwen-3.7-max": 0
},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-10T00:01:00+00:00"
}
}
},
"W3": {
"total_window": 1370,
"total_prev_window": 1340,
"labels": {
"claude-fable-5": "claude-fable-5",
"claude-opus-5": "claude-opus-5",
"deepseek-v4-pro": "deepseek-v4-pro",
"gemini-3.1-pro": "gemini-3.1-pro",
"gpt-5.6-sol": "gpt-5.6-sol",
"grok-4.6": "grok-4.6 (incl. 4.5-era, Aug 17-23)",
"qwen-3.8-max": "qwen-3.8-max"
},
"per_head": {
"claude-fable-5": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-17T00:01:00+00:00"
},
"claude-opus-5": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {
"claude-opus-4.8": 0
},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-17T00:01:00+00:00"
},
"deepseek-v4-pro": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-17T00:01:00+00:00"
},
"gemini-3.1-pro": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-17T00:01:00+00:00"
},
"gpt-5.6-sol": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-17T00:01:00+00:00"
},
"grok-4.6": {
"legacy_ids_seen_in_window": [
"grok-4.5"
],
"n_rows_remapped": {
"grok-4.5": 1370
},
"first_legacy_slot": "2026-08-17T00:01:00+00:00",
"last_legacy_slot": "2026-08-23T23:01:00+00:00",
"first_successor_slot": null
},
"qwen-3.8-max": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {
"qwen-3.7-max": 0
},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-17T00:01:00+00:00"
}
}
},
"W4": {
"total_window": 110,
"total_prev_window": 1370,
"labels": {
"claude-fable-5": "claude-fable-5",
"claude-opus-5": "claude-opus-5",
"deepseek-v4-pro": "deepseek-v4-pro",
"gemini-3.1-pro": "gemini-3.1-pro",
"gpt-5.6-sol": "gpt-5.6-sol",
"grok-4.6": "grok-4.6 (incl. 4.5-era, Aug 24)",
"qwen-3.8-max": "qwen-3.8-max"
},
"per_head": {
"claude-fable-5": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-24T00:01:00+00:00"
},
"claude-opus-5": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {
"claude-opus-4.8": 0
},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-24T00:01:00+00:00"
},
"deepseek-v4-pro": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-24T00:01:00+00:00"
},
"gemini-3.1-pro": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-24T00:01:00+00:00"
},
"gpt-5.6-sol": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-24T00:01:00+00:00"
},
"grok-4.6": {
"legacy_ids_seen_in_window": [
"grok-4.5"
],
"n_rows_remapped": {
"grok-4.5": 110
},
"first_legacy_slot": "2026-08-24T00:01:00+00:00",
"last_legacy_slot": "2026-08-24T09:01:00+00:00",
"first_successor_slot": "2026-08-24T10:01:00+00:00"
},
"qwen-3.8-max": {
"legacy_ids_seen_in_window": [],
"n_rows_remapped": {
"qwen-3.7-max": 0
},
"first_legacy_slot": null,
"last_legacy_slot": null,
"first_successor_slot": "2026-08-24T00:01:00+00:00"
}
}
}
},
"d2_at_cutoff": {
"window_key": "MONTH",
"cutoff": "2026-09-01T16:00:00+00:00",
"canonical_definition": "D2_directional_only",
"canonical_value_at_cutoff": 39073,
"since": "2026-07-11T00:00:00+00:00",
"d1_d3_at_cutoff": {
"D1_expired_ok_in_gate": 83113,
"D2_directional_only": 39073,
"D3_weekly_rule_mature": 82964
},
"marker": "RTD-D2-MONTHLY=39073",
"note": "this is the monthly RTD pin -- the number that goes into the Monthly plain boxes"
},
"prior_window_summary": {
"applicable": true,
"start": "2026-07-01T00:00:00+00:00",
"end": "2026-08-01T00:00:00+00:00",
"effective_start": "2026-07-15T18:01:00+00:00",
"cutoff": "2026-08-01T16:00:00+00:00",
"partial": true,
"note": "forecasts since 2026-07-11; candles since 2026-07-15",
"counters": {
"forecasts_total": 46285,
"ok_in_gate": 42134,
"mature": 41985,
"mature_directional": 19541,
"mature_sideways": 22444
},
"lineage_splice_counts": {
"claude-opus-4.8": 6315,
"grok-4.5": 6608,
"qwen-3.7-max": 6609
},
"field": {
"hit_rate": {
"month": 0.4633,
"prior": 0.4498,
"delta_pp": 1.4
},
"gap_pp": {
"month": 16.3,
"prior": 17.8,
"delta_pp": -1.5
},
"brier": {
"month": 0.2784,
"prior": 0.2831
},
"mean_conf": {
"month": 62.6,
"prior": 62.8
},
"n": {
"month": 19383,
"prior": 19541
}
},
"consensus": {
"lift_pp": {
"month": 1.9,
"prior": -10.6,
"delta_pp": 12.5
},
"n_scoreable": {
"month": 16089,
"prior": 16993
},
"herd_share_pct": {
"month": 98.7,
"prior": 97.4
}
},
"leader": {
"month": "claude-opus-5",
"month_hit_rate": 0.4779,
"prior": "qwen-3.8-max",
"prior_hit_rate": 0.4568
},
"per_model": {
"claude-fable-5": {
"hit_month": 0.4673,
"hit_prior": 0.445,
"hit_delta_pp": 2.2,
"gap_month": 13.9,
"gap_prior": 15.9,
"gap_delta_pp": -2.0,
"n_month": 2812,
"n_prior": 2690
},
"claude-opus-5": {
"hit_month": 0.4779,
"hit_prior": 0.4492,
"hit_delta_pp": 2.9,
"gap_month": 13.2,
"gap_prior": 15.6,
"gap_delta_pp": -2.4,
"n_month": 2281,
"n_prior": 3448
},
"deepseek-v4-pro": {
"hit_month": 0.4554,
"hit_prior": 0.4505,
"hit_delta_pp": 0.5,
"gap_month": 15.4,
"gap_prior": 16.6,
"gap_delta_pp": -1.2,
"n_month": 2578,
"n_prior": 1869
},
"gemini-3.1-pro": {
"hit_month": 0.4761,
"hit_prior": 0.4511,
"hit_delta_pp": 2.5,
"gap_month": 18.8,
"gap_prior": 20.0,
"gap_delta_pp": -1.2,
"n_month": 3033,
"n_prior": 2813
},
"gpt-5.6-sol": {
"hit_month": 0.4586,
"hit_prior": 0.4431,
"hit_delta_pp": 1.6,
"gap_month": 21.8,
"gap_prior": 22.1,
"gap_delta_pp": -0.3,
"n_month": 2970,
"n_prior": 3085
},
"grok-4.6": {
"hit_month": 0.4527,
"hit_prior": 0.453,
"hit_delta_pp": -0.0,
"gap_month": 15.1,
"gap_prior": 14.2,
"gap_delta_pp": 0.9,
"n_month": 2708,
"n_prior": 2265
},
"qwen-3.8-max": {
"hit_month": 0.4565,
"hit_prior": 0.4568,
"hit_delta_pp": -0.0,
"gap_month": 14.7,
"gap_prior": 18.7,
"gap_delta_pp": -4.0,
"n_month": 3001,
"n_prior": 3371
}
},
"per_symbol": {
"BNB": {
"hit_month": 0.4807,
"hit_prior": 0.4548,
"hit_delta_pp": 2.6,
"n_month": 3857,
"n_prior": 2720
},
"BTC": {
"hit_month": 0.4648,
"hit_prior": 0.4418,
"hit_delta_pp": 2.3,
"n_month": 4068,
"n_prior": 4169
},
"ETH": {
"hit_month": 0.4287,
"hit_prior": 0.4781,
"hit_delta_pp": -4.9,
"n_month": 3695,
"n_prior": 4564
},
"SOL": {
"hit_month": 0.4733,
"hit_prior": 0.4325,
"hit_delta_pp": 4.1,
"n_month": 3928,
"n_prior": 3443
},
"XRP": {
"hit_month": 0.4673,
"hit_prior": 0.4455,
"hit_delta_pp": 2.2,
"n_month": 3835,
"n_prior": 3053
}
},
"log_line": "prior_window: n_mature_directional=19541, effective_start=2026-07-15T18:01:00+00:00, field hit=0.4498 gap=17.8, loo lift=-10.6",
"note_definitions": "the prior block is window A of the MONTH pull, matured at the prior cutoff with the same rules; delta = month - prior in percentage points",
"per_symbol_retired_not_compared": [
"AVAX",
"DOGE",
"LINK",
"PEPE",
"TON"
]
},
"note": "controls are DESCRIPTIVE and never fatal; they are printed in the log as well"
}
}