# Weekly Model Watch #9

**WEEKLY · MODEL WATCH** · October 7, 2026 · MarketMania Research · Weekly series

Window: **Sep 28-Oct 4, 2026 UTC** · Cutoff: **Mon Oct 5, 2026, 16:00 UTC** · Methodology **v1.1 (2026-08-10)**, hash `e66c7e8c864a2233`

PDF: https://marketmania.ai/research/reports/model-watch-2026-09-28.pdf · Open data (JSON): https://marketmania.ai/research/reports/model-watch-2026-09-28.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 |  |  |  |
|---|---|---|---|
| **4,331** directional calls scored | **7** models (stable lineup) | of **9,286** mature forecasts | window **Sep 28-Oct 4, 2026 UTC** |
| hit = direction rule: tp1/tp2->hit, sl->miss, expiry->sign of gross pnl | FH gate **1h / 4h / 1d** | base field hit **49.6%** | cutoff **Mon Oct 5, 2026, 16:00 UTC** |
| market: BTC net **+2.44%** (prior +4.06%) | ann vol **21.1%** (was 52.2%) | TOP5 volume **$17.96B**, -20% w/w | pairwise corr **0.57** (was 0.71) |

## Key finding

> **KEY FINDING · OBSERVATION (one weekly window)**
>
> ### Field accuracy went 46.8% -> 49.6% (+2.8pp) with 5 of 7 models improving, and no weekly title was awarded, for the ninth issue running.

## TL;DR

- **OBSERVATION -- No weekly title again.** grok-4.6 leads descriptively at 52.7% [47.9%, 57.3%]; the gap to #2 (deepseek-v4-pro, 50.9%) is 1.7pp. 5 of 7 models improved week over week; issue #8's leader gemini-3.1-pro is now 5 of 7.
- **1 of 5 tickers were readable.** BTC is the week's most readable coin (53.3%, n=944) and SOL the hardest at 46.0%; 1 of the 5 assets cleared 51%. Pair of the week: grok-4.6 x BTC 58.1% (n=93); worst: gpt-5.6-sol x SOL 41.5% (n=130).
- **0 of 2 qualifying turns found a caller.** BTC short -2.28%, 0 caller(s), first NOBODY; ETH short -2.75%, 0 caller(s), first NOBODY.
- **Self-agreement read as a lift in every cell.** Cross-TF/FH lifts ran +0.4pp to +18.7pp (issue #8: -2.5pp to +3.8pp). On trend days, 4h TF-agreement hit 66.9% (n=121) against 42.4% (n=321) 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 46.8% -> 49.6%. The grok column compares two pure grok-4.6 weeks: the 4.5 -> 4.6 flip sits five windows back. "Was" values are the numbers published in issue #8; 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 #8 as well -- the 4.5 -> 4.6 flip sits five 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 five 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 fourth 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 |
|---|---|---|---|---|---|
| grok-4.6 | 431 | 32.6% | 52.7% | 47.9%-57.3% | +5.7 |
| deepseek-v4-pro | 687 | 51.6% | 50.9% | 47.2%-54.7% | +7.1 |
| claude-opus-5 | 534 | 40.2% | 50.7% | 46.5%-55.0% | +3.2 |
| claude-fable-5 | 623 | 46.8% | 49.9% | 46.0%-53.8% | +3.2 |
| gemini-3.1-pro | 694 | 52.2% | 49.0% | 45.3%-52.7% | -2.4 |
| qwen-3.8-max | 711 | 53.5% | 48.9% | 45.3%-52.6% | +4.4 |
| gpt-5.6-sol | 651 | 49.5% | 46.5% | 42.7%-50.4% | -0.2 |

No weekly title is awarded this issue -- for the ninth time. Title rule: **>=5pp gap AND non-overlapping 95% CI, N>=10** per side. grok-4.6's lead over deepseek-v4-pro is 1.7pp and their CIs overlap, so neither condition is met. The grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits five 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 fourth pure-4.6 against pure-4.6 comparison of the series.

## Ticker of the week

| Symbol | N | Hit rate | 95% CI | Issue #8 |
|---|---|---|---|---|
| BTC | 944 | 53.3% | 50.1%-56.5% | 48.9% |
| ETH | 786 | 50.8% | 47.3%-54.2% | 45.8% |
| XRP | 806 | 50.2% | 46.8%-53.7% | 50.0% |
| BNB | 899 | 47.9% | 44.7%-51.2% | 38.2% |
| SOL | 896 | 46.0% | 42.7%-49.3% | 48.7% |

BTC was the field's most readable ticker (53.3%) and SOL the hardest (46.0%); 1 of 5 assets cleared 51% this week (issue #8: 0 of 5). Issue #8's best ticker was XRP and its hardest BNB -- this issue's ordering is BTC > ETH > XRP > BNB > SOL.

## 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 |
|---|---|---|---|
| grok-4.6 | BTC | 93 | 58.1% |
| qwen-3.8-max | BTC | 145 | 56.5% |
| claude-fable-5 | BTC | 131 | 55.7% |
| grok-4.6 | ETH | 73 | 54.8% |
| grok-4.6 | XRP | 81 | 54.3% |
| deepseek-v4-pro | XRP | 125 | 53.6% |

| Model (5 worst) | Symbol | N | Hit rate |
|---|---|---|---|
| qwen-3.8-max | BNB | 150 | 46.7% |
| gpt-5.6-sol | BNB | 136 | 44.9% |
| qwen-3.8-max | SOL | 144 | 44.4% |
| claude-fable-5 | SOL | 135 | 43.0% |
| gpt-5.6-sol | SOL | 130 | 41.5% |

grok-4.6 x BTC (58.1%, n=93) is the week's best pair and gpt-5.6-sol x SOL (41.5%, n=130) the weakest. Pair history accumulates across issues -- read this as the ninth 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].

| Symbol | Time (UTC) | New side | Move (8h) | Callers | First caller |
|---|---|---|---|---|---|
| BTC | Fri Oct 2, 12:00 | Short | -2.28% | 0 | NOBODY |
| ETH | Fri Oct 2, 12:00 | Short | -2.75% | 0 | NOBODY |

The BTC short turn drew NOBODY; the ETH short turn drew NOBODY. Scope in v1 remains BTC/ETH only; the event count across nine issues is still far too small to characterise turn-detection skill either way.

## 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 | 442 | 49.1% | 5 * | 0.0% | 48.7% (548) | +0.4 |
| cross-TF | 1d | TF 1d vs 4h | 33 | 63.6% | 1 * | 100.0% | 57.3% (96) | +6.3 |
| cross-FH | 4h | by FH 1h | 404 | 53.2% | 14 | 21.4% | 48.7% (548) | +4.5 |
| cross-FH | 1d | by FH 4h | 25 | 76.0% | 1 * | 100.0% | 57.3% (96) | +18.7 |

* = N<10 (insufficient); insufficient cells are never used to rank models. Mixed pairs (a model with only one side of the comparison present): 100 / 62 / 129 / 70. Pooled across all four cell families the lifts run +0.4pp to +18.7pp this week (issue #8: -2.5pp to +3.8pp).

**Regime control.** Methodology calls for a trend-vs-flat split on this table. This window has 2 trend days of 7: 09-28 -1.19%, 09-29 +0.22%, 09-30 -0.22%, 10-01 +1.54% (trend), 10-02 -0.39%, 10-03 +0.40%, 10-04 +1.81% (trend). On trend days, 4h TF-agreement hit 66.9% (n=121) against 42.4% (n=321) on flat days.

## Side-mix and the week's failure

| Model | N | Long | Short | Sideways | L:S |
|---|---|---|---|---|---|
| claude-fable-5 | 1,330 | 32.0% | 14.8% | 53.2% | 2.16 |
| claude-opus-5 | 1,330 | 27.4% | 12.8% | 59.9% | 2.14 |
| deepseek-v4-pro | 1,330 | 31.1% | 20.5% | 48.4% | 1.52 |
| gemini-3.1-pro | 1,330 | 31.9% | 20.2% | 47.8% | 1.58 |
| gpt-5.6-sol | 1,315 | 28.4% | 21.1% | 50.5% | 1.34 |
| grok-4.6 | 1,322 | 19.1% | 13.5% | 67.4% | 1.41 |
| qwen-3.8-max | 1,329 | 34.4% | 19.1% | 46.5% | 1.80 |

L:S = each model's own long-share divided by its short-share; the field average of the per-model ratios is 1.71 this week. 'Sideways' was 53.4% of mature forecasts (4,955 of 9,286). Consensus skew: 501 symbol/FH/TF cells had 5 or more models on the same side and hit 51.1% (n=3,247) against the 49.6% field base.

| Model | Symbol | Side | Conf | FH / TF | Slot (UTC) | Exit | Net PnL |
|---|---|---|---|---|---|---|---|
| gemini-3.1-pro | XRP | Long | 85 | 1h / 1h | Oct 4, 08:01 | EXPIRY | -$0.29 |

**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

grok-4.6 is both this week's hit-rate leader (52.7%) and the lowest-Brier line (Brier 0.2566, gap +7.7pp). Per-model ok-rate this window ran 98.98% to 100.00%. The full confidence-bucket analysis lives in Weekly Calibration #9.

## Market check: an up week on lower volatility

> **MARKET CHECK · OBSERVATION (two adjacent calendar weeks)**
>
> OBSERVATION — mean |1d move| 1.83% -> 0.87% (-52% rel), BTC realized vol 35.8% -> 32.2% (ann., hourly); field directional accuracy 46.8% -> 49.6% (+2.8pp), 5 of 7 models improved, sim win-rate up for 5 of 7, field sim PnL -$315.68 -> -$408.24 (adjacent calendar weeks Sep 21-27 vs Sep 28-Oct 4; descriptive, one pair of weeks, not a claim).
>
> Robustness: raw price-sign accuracy 49.2% -> 49.0% — the opposite direction to the trade-based hit rule.

| Measure | Sep 21-27 (week A) | Sep 28-Oct 4 (week B) | Change |
|---|---|---|---|
| Mean \|1d move\| (5 assets) | 1.83% | 0.87% | -52% rel |
| BTC realized vol (ann., hourly) | 35.8% | 32.2% | -3.6pp |
| Field directional accuracy | 46.8% | 49.6% | +2.8pp |
| Models improving hit-rate | -- | 5 of 7 | -- |
| Raw price-sign accuracy | 49.2% | 49.0% | -0.2pp |
| Field sim win-rate | 40.0% | 41.0% | +1.1pp |
| Field sim net PnL | -$315.68 | -$408.24 | -- |

Week A is exactly the issue-#8 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, five windows back, inside issue #4's window). Week A (2026-09-21..2026-09-27) is pure grok-4.6 (it reproduces the published issue #8); 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. Nine issues, and the best ticker changed hands in every one except issue #6 (SOL -> BNB -> BTC -> SOL -> BNB -> BNB -> ETH -> XRP -> BTC): BTC leads this week at 53.3%, after one issue of XRP.
- Self-agreement lifts run +0.4pp to +18.7pp with small disagree cells; carry the regime split into the monthly test, do not act on it.

## Limitations

- Single week (Sep 28-Oct 4, 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 #8: 2 of 7); every comparison with issue #8 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 nine issues cannot characterise detector performance either way.
- Cross-TF and cross-FH disagreement cells are small (n=5, 1, 14, 1); 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 7 still returns deepseek-v4-pro as the served model for our requests, with the same system fingerprint as on Sep 29, so this issue keeps the label; it will change the day the served id changes. On Sep 21, from 04:01 UTC, the provider returned HTTP 402 (insufficient balance) to 20 deepseek-v4-pro calls inside week A (the issue-#8 window), counted as invalid there (invalid 44 in issue #8); in this window the line's ok-rate is 100.0% (invalid 28 this window). Series density and lineage notes (wave 9): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so inside this window (Sep 28-Oct 4) daily coverage is FULL, as it was in issues #4, #5, #6, #7 and #8: 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 486). (2) The grok line flipped 4.5 -> 4.6 at Aug 24, 2026 09:22 UTC, five 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-#8 window), so every grok number in this issue and in issue #8 is a pure grok-4.6 line -- the grok week-over-week row is the fourth 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 #8 after the audit that found the raw table mixes two exchanges; issue #8 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 5 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7 and #8, which printed 57,929 at the Sep 28 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 62,260 is an additive step under one definition; counter deltas against issue #7 and earlier remain definitional.

## Counters & lineage

| Counter | Value | Counter | Value |
|---|---|---|---|
| Forecasts total | 10,290 | Mature (scored pool) | 9,286 |
| OK in gate | 9,286 | -- of them directional | 4,331 |
| Out of gate (1w / 1M) | 490 / 486 | -- of them sideways | 4,955 |
| Invalid | 28 | Pending (next issue) | 0 |
| Late closes | 0 | Uptime, all grids | 266 / 266 slots |
| Source file | weekly_metrics_2026-09-28.json | Report cutoff | Mon Oct 5, 2026, 16:00 UTC |
| Generated at (pipeline) | 2026-10-07 06:16 UTC | Methodology | v1.1 (2026-08-10) · hash e66c7e8c864a2233 |

**THIS REPORT: 4,331 scored observations.** MARKETMANIA RESEARCH TO DATE (as of Oct 5, 2026 cutoff): 62,260 directional forecasts resolved since Jul 11 · 7 models tracked (current line-up; earlier versions folded into their successors' lineage) · 5 assets · 5 horizons · hourly · 45 published reports.

> **Issue #9.** Weekly Model Watch is a living series. Issue #8's open questions -- "does gemini-3.1-pro hold the top rank for a fifth issue, and does the title rule ever fire?" and "Does a qualifying reversal fire outside ETH for a second issue running, and does a second turn in the same pair ever draw a caller?" -- read this issue as: grok-4.6 at the top (52.7%), not the line that led issues #5 to #8 (gemini-3.1-pro), so the rank did not hold for a fifth issue; no weekly title was awarded, for the ninth issue running, and 0 of 2 qualifying turns found a caller, on turns in BTC / ETH; the BTC turn makes a second issue running with a qualifying turn outside ETH, and with one turn per pair the second-turn question stays open. The grok row is pure grok-4.6 this issue and was pure grok-4.6 in issue #8; the 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits five 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 grok-4.6 hold the top rank for a second issue, and does the title rule ever fire?
- 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?
- 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 #9 | https://marketmania.ai/research/reports/consensus-watch-2026-09-28.pdf |
| Weekly Calibration #9 | https://marketmania.ai/research/reports/weekly-calibration-2026-09-28.pdf |
| Weekly Model Watch #8 | https://marketmania.ai/research/reports/model-watch-2026-09-21.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_2026w40,
  title  = {Weekly Model Watch #9: weekly leaderboard, ticker/pair reads and cross-confirmation, Sep 28-Oct 4 2026},
  author = {{MarketMania Research}},
  year   = {2026}, month = {October}, day = {7},
  url    = {https://marketmania.ai/research/reports/model-watch-2026-09-28.pdf},
  note   = {Methodology v1.1 (2026-08-10), hash e66c7e8c864a2233; window Sep 28-Oct 4, 2026 UTC; source weekly_metrics_2026-09-28.json}
}
```
