# Weekly Model Watch #10

**WEEKLY · MODEL WATCH** · October 14, 2026 · MarketMania Research · Weekly series

Window: **Oct 5-11, 2026 UTC** · Cutoff: **Mon Oct 12, 2026, 16:00 UTC** · Methodology **v1.1 (2026-08-10)**, hash `e66c7e8c864a2233`

PDF: https://marketmania.ai/research/reports/model-watch-2026-10-05.pdf · Open data (JSON): https://marketmania.ai/research/reports/model-watch-2026-10-05.json

> Research question: *"who led the week, which tickers were readable, who saw the turn first, and does a model agreeing with itself across timeframes/horizons make its call stronger?"*

## Research Snapshot

| RESEARCH SNAPSHOT |  |  |  |
|---|---|---|---|
| **4,601** directional calls scored | **7** models (stable lineup) | of **9,249** mature forecasts | window **Oct 5-11, 2026 UTC** |
| hit = direction rule: tp1/tp2->hit, sl->miss, expiry->sign of gross pnl | FH gate **1h / 4h / 1d** | base field hit **43.8%** | cutoff **Mon Oct 12, 2026, 16:00 UTC** |
| market: BTC net **-3.19%** (prior +2.44%) | ann vol **27.2%** (was 21.1%) | TOP5 volume **$15.97B**, -11% w/w | pairwise corr **0.85** (was 0.57) |

## Key finding

> **KEY FINDING · OBSERVATION (one weekly window)**
>
> ### Field accuracy went 49.6% -> 43.8% (-5.9pp) with 0 of 7 models improving, and no weekly title was awarded, for the tenth issue running.

## TL;DR

- **OBSERVATION -- No weekly title again.** claude-opus-5 leads descriptively at 47.0% [42.7%, 51.3%]; the gap to #2 (claude-fable-5, 45.0%) is 2.0pp. 0 of 7 models improved week over week; issue #9's leader grok-4.6 is now 5 of 7.
- **No ticker cleared 51%.** BTC is the week's most readable coin (46.1%, n=975) and XRP the hardest at 42.1%; 0 of the 5 assets cleared 51%. Pair of the week: claude-opus-5 x XRP 49.6% (n=117); worst: deepseek-v4-pro x XRP 37.8% (n=156).
- **No qualifying reversal fired.** No BTC/ETH turn met the detector threshold inside this window (detector status no_reversal_events), so there is nothing to score this issue.
- **Self-agreement split across the four cells.** Cross-TF/FH lifts ran -2.0pp to +6.8pp (issue #9: +0.4pp to +18.7pp). On trend days, 4h TF-agreement hit 66.7% (n=237) against 26.2% (n=302) on flat days.

### Week-over-week chart (see PDF for the grouped bar chart)

Directional hit-rate (%) by model, week over week, ranked by this week's rate. Short names: opus-5 = claude-opus-5, fable-5 = claude-fable-5, gemini-3.1 = gemini-3.1-pro, gpt-5.6 = gpt-5.6-sol, qwen-3.8 = qwen-3.8-max, deepseek = deepseek-v4-pro. Field base 49.6% -> 43.8%. The grok column compares two pure grok-4.6 weeks: the 4.5 -> 4.6 flip sits six windows back. "Was" values are the numbers published in issue #9; the leaderboard's W/w column is computed on unrounded rates and can differ by 0.1pp from the difference of the rounded columns.

## Why it matters

MarketMania scores 7 model lines against the same market, hour after hour. Weekly Model Watch asks four practical questions about that week of calls: who led the week, which tickers were readable, who saw the turn first, and does a model agreeing with itself across timeframes/horizons make its call stronger? Each question gets its own block below, with its own table, its own N, and its own honesty caveats. The grok row is a pure grok-4.6 week in this issue and was one in issue #9 as well -- the 4.5 -> 4.6 flip sits six windows back -- so read the grok week-over-week row as a line, not a single model build.

## 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. The weekly 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 wherever the week supplies both sides. The grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits six windows back (issue #4): both weeks of this issue are pure grok-4.6, with no 4.5-era rows in either window, so the grok week-over-week row is the fifth pure-4.6 against pure-4.6 comparison of the series.

## Leaderboard of the week

| Model | N | Cov. | Hit rate | 95% CI | W/w pp |
|---|---|---|---|---|---|
| claude-opus-5 | 517 | 39.8% | 47.0% | 42.7%-51.3% | -3.7 |
| claude-fable-5 | 613 | 47.1% | 45.0% | 41.1%-49.0% | -4.9 |
| gpt-5.6-sol | 734 | 55.2% | 43.5% | 39.9%-47.1% | -3.1 |
| gemini-3.1-pro | 722 | 54.3% | 43.4% | 39.8%-47.0% | -5.6 |
| grok-4.6 | 547 | 41.1% | 43.3% | 39.2%-47.5% | -9.3 |
| qwen-3.8-max | 707 | 53.2% | 43.1% | 39.5%-46.8% | -5.8 |
| deepseek-v4-pro | 761 | 57.2% | 42.0% | 38.6%-45.6% | -8.9 |

No weekly title is awarded this issue -- for the tenth time. Title rule: **>=5pp gap AND non-overlapping 95% CI, N>=10** per side. claude-opus-5's lead over claude-fable-5 is 2.0pp and their CIs overlap, so neither condition is met. The grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits six windows back (issue #4): both weeks of this issue are pure grok-4.6, with no 4.5-era rows in either window, so the grok week-over-week row is the fifth pure-4.6 against pure-4.6 comparison of the series.

## Ticker of the week

| Symbol | N | Hit rate | 95% CI | Issue #9 |
|---|---|---|---|---|
| BTC | 975 | 46.1% | 42.9%-49.2% | 53.3% |
| SOL | 895 | 44.2% | 41.0%-47.5% | 46.0% |
| ETH | 896 | 43.9% | 40.6%-47.1% | 50.8% |
| BNB | 877 | 42.4% | 39.2%-45.7% | 47.9% |
| XRP | 958 | 42.1% | 39.0%-45.2% | 50.2% |

BTC was the field's most readable ticker (46.1%) and XRP the hardest (42.1%); 0 of 5 assets cleared 51% this week (issue #9: 1 of 5). Issue #9's best ticker was BTC and its hardest SOL -- this issue's ordering is BTC > SOL > ETH > BNB > XRP.

## Pair of the week

Top 6 of the 12 model x ticker pairs tracked this week (best hit-rate), then the 5 worst in their own table -- the pair list is split rather than paged so neither table breaks across a page. Pairs shown require N of 8 or more calls.

| Model (top 6) | Symbol | N | Hit rate |
|---|---|---|---|
| claude-opus-5 | XRP | 117 | 49.6% |
| claude-fable-5 | ETH | 122 | 49.2% |
| claude-opus-5 | SOL | 95 | 48.4% |
| gemini-3.1-pro | BTC | 154 | 48.0% |
| claude-opus-5 | ETH | 100 | 48.0% |
| grok-4.6 | BTC | 107 | 47.7% |

| Model (5 worst) | Symbol | N | Hit rate |
|---|---|---|---|
| qwen-3.8-max | BNB | 134 | 40.3% |
| gpt-5.6-sol | XRP | 149 | 40.3% |
| grok-4.6 | BNB | 102 | 40.2% |
| gemini-3.1-pro | XRP | 142 | 38.0% |
| deepseek-v4-pro | XRP | 156 | 37.8% |

claude-opus-5 x XRP (49.6%, n=117) is the week's best pair and deepseek-v4-pro x XRP (37.8%, n=156) the weakest. Pair history accumulates across issues -- read this as the tenth data point, not a ranking.

## Who saw the reversal first

Reversal definition: 4h grid; trend = sign of prior 24h; counter-move of 2.0% or more (BTC/ETH) sustained 8h. A model 'calls' the reversal if it has a matured directional hit call in the new direction, FH 4h or 1d, in the slot window [T-12h, T+FH].

No qualifying reversal fired inside this window (status: no_reversal_events), so the block is empty by construction, not by failure to look.

## Cross-TF and cross-FH confirmation: does agreeing with yourself help?

| Block | FH | vs. | Agree n | Agree hit | Dis n | Dis hit | Base hit | Lift |
|---|---|---|---|---|---|---|---|---|
| cross-TF | 4h | TF 4h vs 1h | 539 | 44.0% | 40 | 62.5% | 45.8% (797) | -1.8 |
| cross-TF | 1d | TF 1d vs 4h | 111 | 24.3% | 2 * | 0.0% | 21.2% (160) | +3.1 |
| cross-FH | 4h | by FH 1h | 493 | 43.8% | 38 | 57.9% | 45.8% (797) | -2.0 |
| cross-FH | 1d | by FH 4h | 89 | 28.1% | 2 * | 0.0% | 21.2% (160) | +6.8 |

* = N<10 (insufficient); insufficient cells are never used to rank models. Mixed pairs (a model with only one side of the comparison present): 218 / 47 / 266 / 69. Pooled across all four cell families the lifts run -2.0pp to +6.8pp this week (issue #9: +0.4pp to +18.7pp).

**Regime control.** Methodology calls for a trend-vs-flat split on this table. This window has 2 trend days of 7: 10-05 -0.61%, 10-06 -0.37%, 10-07 -2.65% (trend), 10-08 -1.81% (trend), 10-09 +1.06%, 10-10 +0.48%, 10-11 +0.93%. On trend days, 4h TF-agreement hit 66.7% (n=237) against 26.2% (n=302) on flat days.

## Side-mix and the week's failure

| Model | N | Long | Short | Sideways | L:S |
|---|---|---|---|---|---|
| claude-fable-5 | 1,300 | 27.1% | 20.1% | 52.8% | 1.35 |
| claude-opus-5 | 1,300 | 20.5% | 19.3% | 60.2% | 1.06 |
| deepseek-v4-pro | 1,330 | 20.8% | 36.5% | 42.8% | 0.57 |
| gemini-3.1-pro | 1,330 | 27.9% | 26.4% | 45.7% | 1.06 |
| gpt-5.6-sol | 1,330 | 20.4% | 34.8% | 44.8% | 0.59 |
| grok-4.6 | 1,330 | 12.9% | 28.2% | 58.9% | 0.46 |
| qwen-3.8-max | 1,329 | 24.5% | 28.7% | 46.8% | 0.86 |

L:S = each model's own long-share divided by its short-share; the field average of the per-model ratios is 0.85 this week. 'Sideways' was 50.3% of mature forecasts (4,648 of 9,249). Consensus skew: 508 symbol/FH/TF cells had 5 or more models on the same side and hit 43.6% (n=3,171) against the 43.8% field base.

| Model | Symbol | Side | Conf | FH / TF | Slot (UTC) | Exit | Net PnL |
|---|---|---|---|---|---|---|---|
| gpt-5.6-sol | BTC | Short | 82 | 4h / 1h | Oct 8, 16:01 | EXPIRY | -$0.97 |

**Fail of the week.** The week's single highest-confidence individual miss, exit reason expiry. Listed as a single card, never as a model ranking.

## Calibration bridge

claude-opus-5 is both this week's hit-rate leader (47.0%) and the lowest-Brier line (Brier 0.2685, gap +13.8pp). Per-model ok-rate this window ran 97.96% to 100.00%. The full confidence-bucket analysis lives in Weekly Calibration #10.

## Market check: a down week with bigger daily moves

> **MARKET CHECK · OBSERVATION (two adjacent calendar weeks)**
>
> OBSERVATION — mean |1d move| 0.87% -> 1.54% (+77% rel), BTC realized vol 32.2% -> 30.9% (ann., hourly); field directional accuracy 49.6% -> 43.8% (-5.9pp), 0 of 7 models improved, sim win-rate up for 0 of 7, field sim PnL -$408.24 -> -$520.82 (adjacent calendar weeks Sep 28-Oct 4 vs Oct 5-11; descriptive, one pair of weeks, not a claim).
>
> Robustness: raw price-sign accuracy 49.0% -> 45.5% — the same direction as the trade-based hit rule.

| Measure | Sep 28-Oct 4 (week A) | Oct 5-11 (week B) | Change |
|---|---|---|---|
| Mean \|1d move\| (5 assets) | 0.87% | 1.54% | +77% rel |
| BTC realized vol (ann., hourly) | 32.2% | 30.9% | -1.3pp |
| Field directional accuracy | 49.6% | 43.8% | -5.9pp |
| Models improving hit-rate | -- | 0 of 7 | -- |
| Raw price-sign accuracy | 49.0% | 45.5% | -3.5pp |
| Field sim win-rate | 41.0% | 34.5% | -6.5pp |
| Field sim net PnL | -$408.24 | -$520.82 | -- |

Week A is exactly the issue-#9 window, so this slice and every week-over-week column in this report compare the same two back-to-back weeks. Descriptive, one pair of weeks; the hit rule is methodology v1.1 (trade-based) and the raw price-sign row is the robustness check (hourly closes at :00 against slots at :01). BTC realized vol here is the hourly-return series from the alive slice; the snapshot row's figure is the audited daily-candle estimate -- different estimators, both reported as measured. Lineage splice ACTIVE: grok-4.5 rows are aggregated into grok-4.6 (flip 2026-08-24T09:22:00+00:00, six windows back, inside issue #4's window). Week A (2026-09-28..2026-10-04) is pure grok-4.6 (it reproduces the published issue #9); week B is pure grok-4.6.

## Practical implications

- Do not read this week's leaderboard as a skill ranking: no title was awarded and the top CIs overlap.
- Treat per-ticker readability as weekly weather. Ten issues, and the best ticker changed hands in every one except issues #6 and #10 (SOL -> BNB -> BTC -> SOL -> BNB -> BNB -> ETH -> XRP -> BTC -> BTC): BTC led issue #9 and leads again at 46.1%.
- Self-agreement lifts run -2.0pp to +6.8pp with small disagree cells; carry the regime split into the monthly test, do not act on it.

## Limitations

- Single week (Oct 5-11, 2026 UTC). Descriptive for this window only; no claim about next week or any model's underlying skill. This window ran 2 trend days of 7 (issue #9: 2 of 7); every comparison with issue #9 is a comparison across regimes as well as across weeks.
- Observations inside one window are not independent, and the 95% Wilson CIs shown throughout are descriptive, not inferential.
- The reversal detector remains v1 and BTC/ETH-only, on price series reconstructed from trade entry prices. 17 events across ten issues cannot characterise detector performance either way.
- Cross-TF and cross-FH disagreement cells are small (n=40, 2, 38, 2); cells under N=10 are insufficient and never used to rank models. Week-over-week deltas are computed on unrounded rates and may differ by 0.1pp from the difference of the rounded columns.
- 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, qwen-3.8-max. DeepSeek announced routing of V4 Pro to V4.1 Flash from Sep 14, 04:00 UTC; an API check on Oct 13 still returns deepseek-v4-pro as the served model for our requests, with the same system fingerprint as on Oct 7, so this issue keeps the label; it will change the day the served id changes. In this window the line's ok-rate is 100.0% (invalid 72 this window). Series density and lineage notes (wave 10): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so inside this window (Oct 5-11) daily coverage is FULL, as it was in issues #4, #5, #6, #7, #8 and #9: the 1w series has slots on 7 of 7 days and the 1M series on 7 of 7 days; both sit outside this report's FH gate (1h/4h/1d) and appear only in the exclusions counter (1w 490, 1M 479). (2) The grok line flipped 4.5 -> 4.6 at Aug 24, 2026 09:22 UTC, six windows back (inside the issue-#4 window): this window carries 1,470 grok rows and none from the 4.5 era, and neither does week A (the issue-#9 window), so every grok number in this issue and in issue #9 is a pure grok-4.6 line -- the grok week-over-week row is the fifth pure-4.6 against pure-4.6 comparison of the series. (3) qwen-3.8-max succeeded qwen-3.7-max on Aug 5, 2026 (fully before this window).
- Market-state row is computed on a single-exchange (binance) daily candle series, as in issue #9 after the audit that found the raw table mixes two exchanges; issue #9 values are as published.
- Research-to-date counter: directional forecasts resolved inside the FH gate (1h/4h/1d) since Jul 11, counted at the issue cutoff (Oct 12 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8 and #9, which printed 62,260 at the Oct 5 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 66,861 is an additive step under one definition; counter deltas against issue #8 and earlier remain definitional.

## Counters & lineage

| Counter | Value | Counter | Value |
|---|---|---|---|
| Forecasts total | 10,290 | Mature (scored pool) | 9,249 |
| OK in gate | 9,249 | -- of them directional | 4,601 |
| Out of gate (1w / 1M) | 490 / 479 | -- of them sideways | 4,648 |
| Invalid | 72 | Pending (next issue) | 0 |
| Late closes | 0 | Uptime, all grids | 266 / 266 slots |
| Source file | weekly_metrics_2026-10-05.json | Report cutoff | Mon Oct 12, 2026, 16:00 UTC |
| Generated at (pipeline) | 2026-10-13 15:15 UTC | Methodology | v1.1 (2026-08-10) · hash e66c7e8c864a2233 |

**THIS REPORT: 4,601 scored observations.** MARKETMANIA RESEARCH TO DATE (as of Oct 12, 2026 cutoff): 66,861 directional forecasts resolved since Jul 11 · 7 models tracked (current line-up; earlier versions folded into their successors' lineage) · 5 assets · 5 horizons · hourly · 53 published reports.

> **Issue #10.** Weekly Model Watch is a living series. Issue #9's open questions -- "does grok-4.6 hold the top rank for a second issue, and does the title rule ever fire?" and "Does a qualifying reversal fire outside ETH for a third issue running, and does a second turn in the same pair ever draw a caller?" -- read this issue as: claude-opus-5 at the top (47.0%), not the line that led issue #9 (grok-4.6), so the rank did not hold for a second issue; no weekly title was awarded, for the tenth issue running, and no qualifying reversal fired, so the run of issues with a qualifying turn outside ETH stops at two (issues #8 and #9) and the second-turn question stays open. The grok row is pure grok-4.6 this issue and was pure grok-4.6 in issue #9; the 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits six windows back. Engine 1.1 has powered the sandbox since Aug 18, i.e. before this window; no cross-engine PnL comparisons are claimed.

## What we're testing next

- Next issue: does claude-opus-5 hold the top rank for a second issue, and does the title rule ever fire?
- Does a qualifying reversal fire again after an issue with none, and does a second turn in the same pair ever draw a caller?
- Monthly series: cross-TF/FH lifts with regime control across mixed weeks (trend vs. flat), block bootstrap.

## Related research

| Report | Direct PDF link |
|---|---|
| Consensus Watch #10 | https://marketmania.ai/research/reports/consensus-watch-2026-10-05.pdf |
| Weekly Calibration #10 | https://marketmania.ai/research/reports/weekly-calibration-2026-10-05.pdf |
| Weekly Model Watch #9 | https://marketmania.ai/research/reports/model-watch-2026-09-28.pdf |

The three weekly reports publish together as one issue each week; each links straight to the others' PDF and to its own previous issue. Direct links are the posting rule from wave 2 on.

## Cite this report

```bibtex
@misc{mm_modelwatch_2026w41,
  title  = {Weekly Model Watch #10: weekly leaderboard, ticker/pair reads and cross-confirmation, Oct 5-11 2026},
  author = {{MarketMania Research}},
  year   = {2026}, month = {October}, day = {14},
  url    = {https://marketmania.ai/research/reports/model-watch-2026-10-05.pdf},
  note   = {Methodology v1.1 (2026-08-10), hash e66c7e8c864a2233; window Oct 5-11, 2026 UTC; source weekly_metrics_2026-10-05.json}
}
```
