# Weekly Model Watch #14

**WEEKLY · MODEL WATCH** · November 11, 2026 · MarketMania Research · Weekly series

Window: **Nov 2-8, 2026 UTC** · Cutoff: **Mon Nov 9, 2026, 16:00 UTC** · Methodology **v1.1 (2026-08-10)**, hash `e66c7e8c864a2233`

PDF: https://marketmania.ai/research/reports/model-watch-2026-11-02.pdf · Open data (JSON): https://marketmania.ai/research/reports/model-watch-2026-11-02.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 |  |  |  |
|---|---|---|---|
| **4,865** directional calls scored | **7** models (stable lineup) | of **9,250** mature forecasts | window **Nov 2-8, 2026 UTC** |
| hit = direction rule: tp1/tp2->hit, sl->miss, expiry->sign of gross pnl | FH gate **1h / 4h / 1d** | base field hit **44.8%** | cutoff **Mon Nov 9, 2026, 16:00 UTC** |
| market: BTC net **-4.47%** (prior -2.25%) | ann vol **55.3%** (was 34.7%) | TOP5 volume **$14.26B**, -4% w/w | pairwise corr **0.94** (was 0.93) |

## Key finding

> **KEY FINDING · OBSERVATION (one weekly window)**
>
> ### Field accuracy went 41.6% -> 44.8% (+3.1pp) with 7 of 7 models improving, and no weekly title was awarded, for the fourteenth issue running.

## TL;DR

- **OBSERVATION -- No weekly title again.** grok-4.7 leads descriptively at 45.9% [42.4%, 49.4%]; the gap to #2 (gpt-6.1-sol, 45.6%) is 0.3pp. 7 of 7 models improved week over week; issue #13's leader grok-4.7 is now 1 of 7.
- **1 of 5 tickers were readable.** XRP is the week's most readable coin (51.7%, n=992) and SOL the hardest at 38.4%; 1 of the 5 assets cleared 51%. Pair of the week: gpt-6.1-sol x XRP 55.6% (n=169); worst: claude-fable-5 x BNB 31.9% (n=116).
- **2 of 5 qualifying turns found a caller.** BTC long +2.54%, 0 caller(s), first NOBODY; BTC short -5.49%, 14 caller(s), first gemini-3.1-pro; ETH long +3.43%, 0 caller(s), first NOBODY; ETH short -7.06%, 11 caller(s), first gpt-6.1-sol; ETH short -5.50%, 0 caller(s), first NOBODY.
- **Self-agreement read as a penalty in every cell.** Cross-TF/FH lifts ran -8.2pp to -2.1pp (issue #13: -4.0pp to +3.9pp). On trend days, 4h TF-agreement hit 49.7% (n=366) against 37.1% (n=221) 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-5.5 = claude-opus-5.5, fable-5 = claude-fable-5, gemini-3.1 = gemini-3.1-pro, gpt-6.1 = gpt-6.1-sol, qwen-3.8 = qwen-3.8-max, deepseek = deepseek-v4-pro. Field base 41.6% -> 44.8%. "Was" values are the numbers published in issue #13; 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 claude-opus-5.5, gpt-6.1-sol and grok-4.7 rows are single-build weeks on the Oct 17 builds in both this issue and issue #13, so those three week-over-week rows compare like with like.

## 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.

## Leaderboard of the week

| Model | N | Cov. | Hit rate | 95% CI | W/w pp |
|---|---|---|---|---|---|
| grok-4.7 | 771 | 58.1% | 45.9% | 42.4%-49.4% | +3.4 |
| gpt-6.1-sol | 807 | 60.7% | 45.6% | 42.2%-49.0% | +3.1 |
| claude-opus-5.5 | 516 | 38.8% | 45.0% | 40.7%-49.3% | +4.0 |
| gemini-3.1-pro | 752 | 56.6% | 44.8% | 41.3%-48.4% | +3.1 |
| deepseek-v4-pro | 754 | 57.1% | 44.6% | 41.0%-48.1% | +3.1 |
| qwen-3.8-max | 663 | 51.6% | 44.5% | 40.8%-48.3% | +3.1 |
| claude-fable-5 | 602 | 45.3% | 42.5% | 38.6%-46.5% | +2.1 |

No weekly title is awarded this issue -- for the fourteenth time. Title rule: **>=5pp gap AND non-overlapping 95% CI, N>=10** per side. grok-4.7's lead over gpt-6.1-sol is 0.3pp and their CIs overlap, so neither condition is met.

## Ticker of the week

| Symbol | N | Hit rate | 95% CI | Issue #13 |
|---|---|---|---|---|
| XRP | 992 | 51.7% | 48.6%-54.8% | 42.7% |
| BTC | 1,049 | 47.8% | 44.8%-50.8% | 42.3% |
| ETH | 966 | 45.6% | 42.5%-48.8% | 41.8% |
| BNB | 858 | 39.5% | 36.3%-42.8% | 36.8% |
| SOL | 1,000 | 38.4% | 35.4%-41.4% | 44.0% |

XRP was the field's most readable ticker (51.7%) and SOL the hardest (38.4%); 1 of 5 assets cleared 51% this week (issue #13: 0 of 5). Issue #13's best ticker was SOL and its hardest BNB -- this issue's ordering is XRP > BTC > ETH > 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 |
|---|---|---|---|
| gpt-6.1-sol | XRP | 169 | 55.6% |
| deepseek-v4-pro | XRP | 161 | 52.8% |
| claude-opus-5.5 | XRP | 104 | 51.9% |
| claude-fable-5 | XRP | 116 | 51.7% |
| grok-4.7 | XRP | 156 | 51.3% |
| grok-4.7 | BTC | 171 | 50.9% |

| Model (5 worst) | Symbol | N | Hit rate |
|---|---|---|---|
| deepseek-v4-pro | SOL | 144 | 38.2% |
| claude-opus-5.5 | SOL | 103 | 37.9% |
| grok-4.7 | SOL | 151 | 37.1% |
| qwen-3.8-max | SOL | 134 | 34.3% |
| claude-fable-5 | BNB | 116 | 31.9% |

gpt-6.1-sol x XRP (55.6%, n=169) is the week's best pair and claude-fable-5 x BNB (31.9%, n=116) the weakest. Pair history accumulates across issues -- read this as the fourteenth 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 | Wed Nov 4, 04:00 | Long | +2.54% | 0 | NOBODY |
| BTC | Thu Nov 5, 08:00 | Short | -5.49% | 14 | gemini-3.1-pro |
| ETH | Wed Nov 4, 04:00 | Long | +3.43% | 0 | NOBODY |
| ETH | Thu Nov 5, 08:00 | Short | -7.06% | 11 | gpt-6.1-sol |
| ETH | Sun Nov 8, 16:00 | Short | -5.50% | 0 | NOBODY |

The BTC long turn drew NOBODY; the BTC short turn drew 14 caller(s), first gemini-3.1-pro on a 1d/4h call at Nov 6, 00:01 with confidence 75; the ETH long turn drew NOBODY; the ETH short turn drew 11 caller(s), first gpt-6.1-sol on a 1d/4h call at Nov 6, 00:01 with confidence 73; the ETH short turn drew NOBODY. Scope in v1 remains BTC/ETH only; the event count across fourteen 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 | 587 | 45.0% | 14 | 57.1% | 47.0% (882) | -2.1 |
| cross-TF | 1d | TF 1d vs 4h | 121 | 48.8% | 8 * | 62.5% | 51.8% (166) | -3.0 |
| cross-FH | 4h | by FH 1h | 505 | 44.2% | 35 | 60.0% | 47.0% (882) | -2.9 |
| cross-FH | 1d | by FH 4h | 101 | 43.6% | 8 * | 62.5% | 51.8% (166) | -8.2 |

* = N<10 (insufficient); insufficient cells are never used to rank models. Mixed pairs (a model with only one side of the comparison present): 276 / 37 / 338 / 57. Pooled across all four cell families the lifts run -8.2pp to -2.1pp this week (issue #13: -4.0pp to +3.9pp).

**Regime control.** Methodology calls for a trend-vs-flat split on this table. This window has trend on 4 of 7 days: 11-02 -2.04% (trend), 11-03 +0.92%, 11-04 +3.90% (trend), 11-05 -5.33% (trend), 11-06 -0.47%, 11-07 -0.07%, 11-08 -1.60% (trend). On trend days, 4h TF-agreement hit 49.7% (n=366) against 37.1% (n=221) on flat days.

## Side-mix and the week's failure

| Model | N | Long | Short | Sideways | L:S |
|---|---|---|---|---|---|
| claude-fable-5 | 1,330 | 25.0% | 20.2% | 54.7% | 1.24 |
| claude-opus-5.5 | 1,330 | 18.8% | 20.0% | 61.2% | 0.94 |
| deepseek-v4-pro | 1,320 | 22.4% | 34.7% | 42.9% | 0.65 |
| gemini-3.1-pro | 1,329 | 24.8% | 31.8% | 43.4% | 0.78 |
| gpt-6.1-sol | 1,330 | 15.9% | 44.8% | 39.3% | 0.35 |
| grok-4.7 | 1,327 | 22.7% | 35.4% | 41.9% | 0.64 |
| qwen-3.8-max | 1,284 | 23.4% | 28.3% | 48.4% | 0.83 |

L:S = each model's own long-share divided by its short-share; the field average of the per-model ratios is 0.77 this week. 'Sideways' was 47.4% of mature forecasts (4,385 of 9,250). Consensus skew: 532 symbol/FH/TF cells had 5 or more models on the same side and hit 44.2% (n=3,390) against the 44.8% field base.

| Model | Symbol | Side | Conf | FH / TF | Slot (UTC) | Exit | Net PnL |
|---|---|---|---|---|---|---|---|
| gemini-3.1-pro | BTC | Long | 80 | 1d / 4h | Nov 5, 00:01 | SL | -$2.60 |

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

## Calibration bridge

The hit-rate leader this week is grok-4.7 (45.9%); the lowest-Brier line is claude-opus-5.5 (Brier 0.2609, gap +11.3pp). Per-model ok-rate this window ran 96.87% to 100.00%. The full confidence-bucket analysis lives in Weekly Calibration #14.

## Market check: bigger daily moves on lower volume

> **MARKET CHECK · OBSERVATION (two adjacent calendar weeks)**
>
> OBSERVATION — mean |1d move| 1.63% -> 2.16% (+33% rel), BTC realized vol 37.0% -> 41.0% (ann., hourly); field directional accuracy 41.6% -> 44.8% (+3.1pp), 7 of 7 models improved, sim win-rate up for 7 of 7, field sim PnL -$869.65 -> -$464.89 (adjacent calendar weeks Oct 26-Nov 1 vs Nov 2-8; descriptive, one pair of weeks, not a claim).
>
> Robustness: raw price-sign accuracy 42.8% -> 48.9% — the same direction as the trade-based hit rule.

| Measure | Oct 26-Nov 1 (week A) | Nov 2-8 (week B) | Change |
|---|---|---|---|
| Mean \|1d move\| (5 assets) | 1.63% | 2.16% | +33% rel |
| BTC realized vol (ann., hourly) | 37.0% | 41.0% | +4.0pp |
| Field directional accuracy | 41.6% | 44.8% | +3.1pp |
| Models improving hit-rate | -- | 7 of 7 | -- |
| Raw price-sign accuracy | 42.8% | 48.9% | +6.0pp |
| Field sim win-rate | 33.6% | 37.4% | +3.8pp |
| Field sim net PnL | -$869.65 | -$464.89 | -- |

Week A is exactly the issue-#13 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 note: the model cutover (2026-10-17T09:01:00+00:00, day 6 of 7 of its Mon-Sun week) sits three windows back, inside the published issue-#11 window, where it spliced three lines -- gpt-5.6-sol -> gpt-6.1-sol, claude-opus-5 -> claude-opus-5.5, grok-4.6 -> grok-4.7. Week A (2026-10-26..2026-11-01, the published issue-#13 window) and week B (2026-11-02..2026-11-08) are both full weeks on the heads (0 and 0 old-id row(s) remapped); week A reproduces the published issue #13. The grok 4.5 -> 4.6 flip (2026-08-24T09:22:00+00:00) sits ten windows back (inside issue #4's window).

## 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. Fourteen issues, and the best ticker changed hands in every one except issues #6, #10 and #12 (SOL -> BNB -> BTC -> SOL -> BNB -> BNB -> ETH -> XRP -> BTC -> BTC -> XRP -> XRP -> SOL -> XRP): XRP leads this week at 51.7%, after SOL in issue #13.
- Self-agreement lifts run -8.2pp to -2.1pp with small disagree cells; carry the regime split into the monthly test, do not act on it.

## Limitations

- Single week (Nov 2-8, 2026 UTC). Descriptive for this window only; no claim about next week or any model's underlying skill. This window had trend on 4 of 7 days (issue #13: 1 of 7); every comparison with issue #13 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. 37 events across fourteen issues cannot characterise detector performance either way.
- Cross-TF and cross-FH disagreement cells are small (n=14, 8, 35, 8); 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-5.5, deepseek-v4-pro, gemini-3.1-pro, gpt-6.1-sol, grok-4.7, qwen-3.8-max. DeepSeek announced routing of V4 Pro to V4.1 Flash from Sep 14, 04:00 UTC; an API check on Nov 10 still returns deepseek-v4-pro as the served model for our requests, with the same system fingerprint as on Nov 3, so this issue keeps the label; it will change the day the served id changes. In this window the line's ok-rate is 99.9% (invalid 1 of its 1,461 rows; 54 across all lines this window). Provider incident: on Nov 5 the provider behind qwen-3.8-max rejected 46 of its 210 first-attempt forecasts with an input-moderation error; those rows are counted in Invalid. From Nov 6 the engine retries such a call without the news block; 2 forecasts in this window (qwen-3.8-max: 2 on Nov 7) were produced that way and are flagged `news_stripped` in the open data. Hit rates in this report use the rows that resolved. Series density and lineage notes (wave 14): (1) rolling-1w forecasts emit daily since Aug 22, 2026 and rolling-1M daily since Aug 23, 2026, so inside this window (Nov 2-8) daily coverage is FULL, as it was in issues #4, #5, #6, #7, #8, #9, #10, #11, #12 and #13: 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 487). (2) This window is the third full week on the builds that took over at Oct 17, 2026 09:01 UTC: claude-opus-5.5, gpt-6.1-sol and grok-4.7 carry no rows from the old builds in either week, and the 7 lines carry 1,461 / 1,470 rows in this window and 1,470 in week A, so every week-over-week row compares two full weeks on the same builds. (3) No roll-out slot of the flip falls inside either week: the two hourly slots before it (Oct 17, 07:01 and 08:01 UTC) lie three windows back, so this window's invalid counter holds none of their rows. (4) Past lineage flips: the Oct 17, 2026 09:01 UTC flip sits three windows back (inside the issue-#11 window), the grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits ten windows back (inside the issue-#4 window), and 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 #13 after the audit that found the raw table mixes two exchanges; issue #13 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 (Nov 9 16:00 UTC) -- the definition pinned in issue #3 and carried by issues #4, #5, #6, #7, #8, #9, #10, #11, #12 and #13, which printed 82,895 at the Nov 2 16:00 cutoff. The pack reproduces that pin at the previous cutoff (control OK), so this issue's 87,760 is an additive step under one definition; counter deltas against issue #12 and earlier remain definitional.

## Counters & lineage

| Counter | Value | Counter | Value |
|---|---|---|---|
| Forecasts total | 10,281 | Mature (scored pool) | 9,250 |
| OK in gate | 9,250 | -- of them directional | 4,865 |
| Out of gate (1w / 1M) | 490 / 487 | -- of them sideways | 4,385 |
| Invalid | 54 | Pending (next issue) | 0 |
| Late closes | 0 | Uptime, all grids | 266 / 266 slots |
| Source file | weekly_metrics_2026-11-02.json | Report cutoff | Mon Nov 9, 2026, 16:00 UTC |
| Generated at (pipeline) | 2026-11-10 14:05 UTC | Methodology | v1.1 (2026-08-10) · hash e66c7e8c864a2233 |

**THIS REPORT: 4,865 scored observations.** MARKETMANIA RESEARCH TO DATE (as of Nov 9, 2026 cutoff): 87,760 directional forecasts resolved since Jul 11 · 7 models tracked (current line-up; earlier versions folded into their successors' lineage) · 5 assets · 5 horizons · hourly · 73 published reports.

> **Issue #14.** Weekly Model Watch is a living series. Issue #13's open questions -- "does grok-4.7 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 fourth issue running, and does a second turn in the same pair draw a caller?" -- read this issue as: grok-4.7 at the top (45.9%), the same line that led issue #13 (grok-4.7), so the rank held for a second issue; no weekly title was awarded, for the fourteenth issue running, and 2 of 5 qualifying turns found a caller, on turns in BTC / ETH; the two BTC turns fired outside ETH for a fourth issue running, and the second turn in each pair (Thu Nov 5, 08:00) drew callers -- 14 on BTC and 11 on ETH -- while the third ETH turn (Sun Nov 8, 16:00) drew NOBODY. The claude-opus-5.5, gpt-6.1-sol and grok-4.7 rows are the third full week on the Oct 17 builds; week-over-week rows compare two full weeks on the same builds. The grok 4.5 -> 4.6 flip (Aug 24, 2026 09:22 UTC) sits ten 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-4.7 hold the top rank for a third issue, and does the title rule ever fire?
- Does a qualifying reversal fire outside ETH for a fifth issue running, and does a second turn in the same pair draw a caller again?
- 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 #14 | https://marketmania.ai/research/reports/consensus-watch-2026-11-02.pdf |
| Weekly Calibration #14 | https://marketmania.ai/research/reports/weekly-calibration-2026-11-02.pdf |
| Weekly Model Watch #13 | https://marketmania.ai/research/reports/model-watch-2026-10-26.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_2026w45,
  title  = {Weekly Model Watch #14: weekly leaderboard, ticker/pair reads and cross-confirmation, Nov 2-8 2026},
  author = {{MarketMania Research}},
  year   = {2026}, month = {November}, day = {11},
  url    = {https://marketmania.ai/research/reports/model-watch-2026-11-02.pdf},
  note   = {Methodology v1.1 (2026-08-10), hash e66c7e8c864a2233; window Nov 2-8, 2026 UTC; source weekly_metrics_2026-11-02.json}
}
```
