Sign up and get 3 free requests with Start plan accessSign up →

Gemini 3.1 Pro

gemini-3.1-pro

Research profile — published report figures only.

Tracked since Aug 3-9, 2026 UTC, first published 10 Aug 2026.

Live benchmark page →All modelsResearch

Research benchmark — not financial or investment advice; paper trading only.

Current standing

Where Gemini 3.1 Pro finished in the most recent published window — the figures the issue printed, not a live reading.

Hit rate
51.4%
95% Wilson [47.9%, 54.9%]
Scored calls
794
directional calls in the window
Rank
#1 of 7
by hit rate, this issue
Coverage
59.7%
calls scored divided by the mature calls available to that model
vs prior window
-1.5pp
52.9% → 51.4%

Weekly Model Watch #8 · Sep 21-27, 2026 UTC · cutoff Mon 28 Sept 2026 16:00 UTC · 51.4% is 4.6pp above the all-model figure of 46.8% for the same window

Hit rate follows the benchmark's TP/SL/expiry outcome rules; it is not simply the asset's price direction at the end of the forecast horizon. The weekly and monthly metrics shown here use the 1h, 4h and 1d horizons; stability runs have their own test coverage.

Monthly hit rate
47.6%
95% Wilson [45.8%, 49.4%]
Monthly calls
3,033
directional calls in the month
Monthly rank
#2 of 7
by hit rate, this issue

Monthly Model Watch #1 · Aug 1-31, 2026 UTC · cutoff Tue 1 Sept 2026 16:00 UTC

Calibration

Stated confidence against realised accuracy. The pooled all-model row of the same table is printed next to Gemini 3.1 Pro's, because a gap only means something against the population it was measured in.

ScopenHit rateMean stated conf.GapBrier95% Wilson
Weekly Calibration #8Gemini 3.1 Pro79451.4%67.6%+16.2pp0.2764[47.9%, 54.9%]
Weekly Calibration #8field, all models4,95846.8%63.0%+16.1pp0.2751—
Monthly Calibration #1Gemini 3.1 Pro3,03347.6%66.4%+18.8pp0.2881[45.8%, 49.4%]
Monthly Calibration #1field, all models19,38346.3%62.6%+16.3pp0.2784—

Weekly Calibration #8 · Sep 21-27, 2026 UTC · cutoff Mon 28 Sept 2026 16:00 UTC — Monthly Calibration #1 · Aug 1-31, 2026 UTC · cutoff Tue 1 Sept 2026 16:00 UTC

Gap vs prior window. 14.0pp → 16.2pp (+2.2pp), as Weekly Calibration #8 printed it.
Stated confidence bucketnHit rateMean stated conf.
50-603n < 10n < 10
60-7045650.0%63.4%
70-8032053.4%73.1%
80-1001553.3%80.0%

Buckets as Weekly Calibration #8 printed them; a cell the issue marked insufficient or empty keeps its count and prints no rate.

Stability

How much Gemini 3.1 Pro's answer moves when nothing else does: identical payloads replayed several times, counted as unanimous sets and as flips. The caption on each tile is the same measurement in the comparison run shipped with the issue.

Unanimity
59.3%
baseline (Jul 31): 33.3%
Hard flips
1
baseline (Jul 31): 0
Soft flips
9
baseline (Jul 31): 15
Invalid
1.5%
baseline (Jul 31): 5.2%
Sideways
54.1%
baseline (Jul 31): 46.9%
Confidence SD
3.2pp
baseline (Jul 31): 3.5pp

Stability Index — Run 2 · 10 Aug 2026 · 945 calls, 5 repeats per set, 27 sets per model, 3 tickers · compared against baseline (Jul 31)

By horizon

Gemini 3.1 Pro split by forecast horizon, as the Calibration issues print it. Only the horizons inside the reports' scoring gate appear here; a cell the builder annotated keeps its annotation.

HorizonWeekly nWeekly hit rateMonthly nMonthly hit rate
1H50051.6%1,95147.4%
4H23752.3%91246.6%
1D5745.6%17055.3%

Weekly Calibration #8 · Sep 21-27, 2026 UTC · cutoff Mon 28 Sept 2026 16:00 UTC — Monthly Calibration #1 · Aug 1-31, 2026 UTC · cutoff Tue 1 Sept 2026 16:00 UTC

By asset

The Model Watch issues print a best-pairs and a worst-pairs table — the model-instrument cells that stood out in the window. Only Gemini 3.1 Pro's own rows are listed; a model that made neither list simply has no row there.

InstrumentListnHit rateIssue
SOLbest pairs18654.3%Weekly Model Watch #8
BTCbest pairs15453.3%Weekly Model Watch #8
XRPbest pairs18153.0%Weekly Model Watch #8
ETHbest pairs14252.1%Weekly Model Watch #8
XRPbest pairs64049.7%Monthly Model Watch #1
BNBbest pairs56849.6%Monthly Model Watch #1

Weekly Model Watch #8 · Sep 21-27, 2026 UTC · cutoff Mon 28 Sept 2026 16:00 UTC — Monthly Model Watch #1 · Aug 1-31, 2026 UTC · cutoff Tue 1 Sept 2026 16:00 UTC

Long
41.1%
share of the model's calls
Short
18.6%
share of the model's calls
Sideways
40.3%
share of the model's calls
Long / short
2.21
ratio, not a share
Mature calls
1,330
behind the mix

Weekly Model Watch #8 · Sep 21-27, 2026 UTC · cutoff Mon 28 Sept 2026 16:00 UTC

Consensus

Forecasts are grouped by whether their direction matched or opposed the leave-one-out majority of the other eligible model lines. Gemini 3.1 Pro is scored separately on each group.

ScopeAgree nAgree hit rateDisagree nDisagree hit rateLiftThin or tied
Consensus Watch #862548.3%1675.0%-26.7pp153
Monthly Consensus Watch #12,24945.4%8947.2%-1.7pp695

leave-one-out: matched vs opposed the majority of the other model lines · Consensus Watch #8 · Sep 21-27, 2026 UTC · cutoff Mon 28 Sept 2026 16:00 UTC — Monthly Consensus Watch #1 · Aug 1-31, 2026 UTC · cutoff Tue 1 Sept 2026 16:00 UTC

Paper trading (scored separately from prediction quality)

What a mechanical paper-trading rule made of Gemini 3.1 Pro's forecasts in the same windows. These figures are kept apart from the accuracy and calibration figures above: a model can be well calibrated and unprofitable, or profitable and badly calibrated.

ScopeTradesWin rateNet PnLGross PnLMax drawdown
Weekly Calibration #879443.0%-$5.94$73.46-$99.60
Monthly Calibration #13,03336.3%-$98.64$204.66-$197.07

Weekly Calibration #8 · Sep 21-27, 2026 UTC · cutoff Mon 28 Sept 2026 16:00 UTC — Monthly Calibration #1 · Aug 1-31, 2026 UTC · cutoff Tue 1 Sept 2026 16:00 UTC

Published history

Every window Gemini 3.1 Pro's slot has been published in, oldest first. Model Watch supplies the count, the hit rate, the interval and the rank; Calibration adds Brier, the gap and the mean stated confidence. The two cadences are separate tables because a month and a week are different windows over the same forecasts, and a window an older issue also filed under a superseded id keeps that reading on its own line: no issue published the two as one figure.

Weekly windows

8 published windows, from Aug 3-9, 2026 UTC to Sep 21-27, 2026 UTC
IssueWindownHit rate95% WilsonRankBrierGapMean stated conf.
#1 · Model Watch · CalibrationAug 3-9, 2026 UTC62943.7%[39.9%, 47.6%]#20.3038+22.2pp65.9%
#2 · Model Watch · CalibrationAug 10-16, 2026 UTC55547.0%[42.9%, 51.2%]#10.2848+18.4pp65.4%
#3 · Model Watch · CalibrationAug 17-23, 2026 UTC79854.1%[50.7%, 57.6%]#30.2646+13.1pp67.2%
#4 · Model Watch · CalibrationAug 24-30, 2026 UTC75544.2%[40.7%, 47.8%]#20.3025+22.5pp66.7%
#5 · Model Watch · CalibrationAug 31-Sep 6, 2026 UTC76146.5%[43.0%, 50.1%]#10.2922+19.7pp66.2%
#6 · Model Watch · CalibrationSep 7-13, 2026 UTC67341.8%[38.1%, 45.5%]#10.3057+23.6pp65.4%
#7 · Model Watch · CalibrationSep 14-20, 2026 UTC88352.9%[49.6%, 56.2%]#10.2701+14.0pp66.8%
#8 · Model Watch · CalibrationSep 21-27, 2026 UTC79451.4%[47.9%, 54.9%]#10.2764+16.2pp67.6%

Monthly windows

1 published window: Aug 1-31, 2026 UTC
IssueWindownHit rate95% WilsonRankBrierGapMean stated conf.
#1 · Model Watch · CalibrationAug 1-31, 2026 UTC3,03347.6%[45.8%, 49.4%]#20.2881+18.8pp66.4%

Each figure is the one its issue froze.

Definitions & method

Quoted from the issues these figures come from.

  • Hit. direction: exit tp1/tp2 -> hit, sl -> miss, expiry -> sign of gross pnl
  • Reading the hit rate. Hit rate follows the benchmark's TP/SL/expiry outcome rules; it is not simply the asset's price direction at the end of the forecast horizon. The weekly and monthly metrics shown here use the 1h, 4h and 1d horizons; stability runs have their own test coverage.
  • Scored pool. directional forecasts resolved inside the FH gate (1h/4h/1d) since Jul 11, at the issue cutoff
  • Gap and Brier. Gap pp = mean stated confidence minus hit-rate, in percentage points; positive means overconfident.
  • Coverage. calls scored divided by the mature calls available to that model
  • Confidence buckets. Models report confidence at discrete levels, not a continuous scale; the buckets reflect those natural breakpoints. Cells below N=10 are marked insufficient.
  • Wilson intervals. 95% Wilson CIs shown are descriptive, not inferential: observations inside one window are dependent, so read them as a range, not a formal coverage guarantee.
  • Weekly title. >=5pp gap AND non-overlapping 95% CI, N>=10
  • Paper trading. A mechanical simulation on Binance USDT-M futures, scored separately from prediction quality and reported on its own. The starting bank, the per-trade notional and the taker fee are set out on Benchmarks methodology.

Methodology v1.1 (2026-08-10) · hash e66c7e8c864a2233 · Methodology · Benchmarks methodology · Dataset