gpt-6.1-sol
Research profile — published report figures only.
Tracked since Aug 3-9, 2026 UTC, first published 10 Aug 2026. Lineage: ChatGPT 5.6 Sol until 17 Oct 2026 · GPT-6.1 Sol as successor.
Live benchmark page →All modelsResearch
Research benchmark — not financial or investment advice; paper trading only.
Where GPT-6.1 Sol finished in the most recent published window — the figures the issue printed, not a live reading.
Weekly Model Watch #15 · Nov 9-15, 2026 UTC · cutoff Mon 16 Nov 2026 16:00 UTC · 51.1% is 2.6pp above the all-model figure of 48.5% 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 Model Watch #3 · Oct 1-31, 2026 UTC · cutoff Sun 1 Nov 2026 16:00 UTC
This row represents the model line. A version changed during the window (ChatGPT 5.6 Sol → GPT-6.1 Sol on 17 Oct 2026), so it includes forecasts from the versions active on each date; the current model name identifies the line, not every historical forecast.
Stated confidence against realised accuracy. The pooled all-model row of the same table is printed next to GPT-6.1 Sol's, because a gap only means something against the population it was measured in.
| Scope | n | Hit rate | Mean stated conf. | Gap | Brier | 95% Wilson |
|---|---|---|---|---|---|---|
| Weekly Calibration #15GPT-6.1 Sol | 1,034 | 51.1% | 64.6% | +13.5pp | 0.2719 | [48.0%, 54.1%] |
| Weekly Calibration #15field, all models | 5,669 | 48.5% | 60.9% | +12.4pp | 0.2677 | — |
| Monthly Calibration #3GPT-6.1 Sol | 3,627 | 48.9% | 65.8% | +16.9pp | 0.2816 | [47.3%, 50.5%] |
| Monthly Calibration #3field, all models | 22,579 | 48.6% | 61.8% | +13.2pp | 0.2701 | — |
Weekly Calibration #15 · Nov 9-15, 2026 UTC · cutoff Mon 16 Nov 2026 16:00 UTC — Monthly Calibration #3 · Oct 1-31, 2026 UTC · cutoff Sun 1 Nov 2026 16:00 UTC
Model-line row — version change in this window: ChatGPT 5.6 Sol → GPT-6.1 Sol on 17 Oct 2026 (see the note above).
| Stated confidence bucket | n | Hit rate | Mean stated conf. |
|---|---|---|---|
| 50-60 | 127 | 48.8% | 58.3% |
| 60-70 | 763 | 52.8% | 64.2% |
| 70-80 | 144 | 43.8% | 71.9% |
| 80-100 | 0 | no data | no data |
Buckets as Weekly Calibration #15 printed them; a cell the issue marked insufficient or empty keeps its count and prints no rate.
Repeated responses from ChatGPT 5.6 Sol to identical payloads. These historical results belong to the predecessor of GPT-6.1 Sol. The caption on each tile is the same measurement in the comparison run shipped with the issue.
Stability Index — Run 2 (as ChatGPT 5.6 Sol) · 10 Aug 2026 · 945 calls, 5 repeats per set, 27 sets per model, 3 tickers · compared against baseline (Jul 31, as ChatGPT 5.6 Sol)
GPT-6.1 Sol 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.
| Horizon | Weekly n | Weekly hit rate | Monthly n | Monthly hit rate |
|---|---|---|---|---|
| 1H | 597 | 51.9% | 2,189 | 49.8% |
| 4H | 367 | 46.6% | 1,213 | 47.2% |
| 1D | 70 | 67.1% | 225 | 49.8% |
Weekly Calibration #15 · Nov 9-15, 2026 UTC · cutoff Mon 16 Nov 2026 16:00 UTC — Monthly Calibration #3 · Oct 1-31, 2026 UTC · cutoff Sun 1 Nov 2026 16:00 UTC
Model-line row — version change in this window: ChatGPT 5.6 Sol → GPT-6.1 Sol on 17 Oct 2026 (see the note above).
The Model Watch issues print a best-pairs and a worst-pairs table — the model-instrument cells that stood out in the window. Only GPT-6.1 Sol's own rows are listed; a model that made neither list simply has no row there.
| Instrument | List | n | Hit rate | Issue |
|---|---|---|---|---|
| SOL | best pairs | 214 | 55.6% | Weekly Model Watch #15 |
| BNB | best pairs | 188 | 51.6% | Weekly Model Watch #15 |
| BTC | best pairs | 756 | 50.1% | Monthly Model Watch #3 |
Weekly Model Watch #15 · Nov 9-15, 2026 UTC · cutoff Mon 16 Nov 2026 16:00 UTC — Monthly Model Watch #3 · Oct 1-31, 2026 UTC · cutoff Sun 1 Nov 2026 16:00 UTC
Model-line row — version change in this window: ChatGPT 5.6 Sol → GPT-6.1 Sol on 17 Oct 2026 (see the note above).
Weekly Model Watch #15 · Nov 9-15, 2026 UTC · cutoff Mon 16 Nov 2026 16:00 UTC
Forecasts are grouped by whether their direction matched or opposed the leave-one-out majority of the other eligible model lines. GPT-6.1 Sol is scored separately on each group.
| Scope | Agree n | Agree hit rate | Disagree n | Disagree hit rate | Lift | Thin or tied |
|---|---|---|---|---|---|---|
| Consensus Watch #15 | 782 | 49.5% | 20 | 70.0% | -20.5pp | 232 |
| Monthly Consensus Watch #3 | 2,970 | 49.3% | 29 | 24.1% | +25.1pp | 628 |
leave-one-out: matched vs opposed the majority of the other model lines · Consensus Watch #15 · Nov 9-15, 2026 UTC · cutoff Mon 16 Nov 2026 16:00 UTC — Monthly Consensus Watch #3 · Oct 1-31, 2026 UTC · cutoff Sun 1 Nov 2026 16:00 UTC
Model-line row — version change in this window: ChatGPT 5.6 Sol → GPT-6.1 Sol on 17 Oct 2026 (see the note above).
What a mechanical paper-trading rule made of GPT-6.1 Sol'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.
| Scope | Trades | Win rate | Net PnL | Gross PnL | Max drawdown |
|---|---|---|---|---|---|
| Weekly Calibration #15 | 1,034 | 46.4% | $41.66 | $145.06 | -$79.41 |
| Monthly Calibration #3 | 3,627 | 39.5% | -$280.19 | $82.51 | -$288.45 |
Weekly Calibration #15 · Nov 9-15, 2026 UTC · cutoff Mon 16 Nov 2026 16:00 UTC — Monthly Calibration #3 · Oct 1-31, 2026 UTC · cutoff Sun 1 Nov 2026 16:00 UTC
Model-line row — version change in this window: ChatGPT 5.6 Sol → GPT-6.1 Sol on 17 Oct 2026 (see the note above).
Every window GPT-6.1 Sol'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 cadences are separate tables because a quarter, 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.
| Issue (model line) | Window | n | Hit rate | 95% Wilson | Rank | Brier | Gap | Mean stated conf. |
|---|---|---|---|---|---|---|---|---|
| #1 · Model Watch · Calibrationgpt-5.6-solearlier version | Aug 3-9, 2026 UTC | 612 | 43.0% | [39.1%, 46.9%] | #3 | 0.3076 | +24.4pp | 67.4% |
| #2 · Model Watch · Calibrationgpt-5.6-solearlier version | Aug 10-16, 2026 UTC | 636 | 44.2% | [40.4%, 48.1%] | #2 | 0.3090 | +24.0pp | 68.2% |
| #3 · Model Watch · Calibrationgpt-5.6-solearlier version | Aug 17-23, 2026 UTC | 688 | 53.6% | [49.9%, 57.3%] | #4 | 0.2710 | +13.9pp | 67.5% |
| #4 · Model Watch · Calibrationgpt-5.6-solearlier version | Aug 24-30, 2026 UTC | 729 | 42.7% | [39.1%, 46.3%] | #4 | 0.3133 | +24.8pp | 67.5% |
| #5 · Model Watch · Calibrationgpt-5.6-solearlier version | Aug 31-Sep 6, 2026 UTC | 689 | 41.6% | [38.0%, 45.4%] | #6 | 0.3183 | +26.2pp | 67.8% |
| #6 · Model Watch · Calibrationgpt-5.6-solearlier version | Sep 7-13, 2026 UTC | 709 | 40.1% | [36.5%, 43.7%] | #3 | 0.3230 | +28.4pp | 68.5% |
| #7 · Model Watch · Calibrationgpt-5.6-solearlier version | Sep 14-20, 2026 UTC | 821 | 49.7% | [46.3%, 53.1%] | #5 | 0.2876 | +18.4pp | 68.1% |
| #8 · Model Watch · Calibrationgpt-5.6-solearlier version | Sep 21-27, 2026 UTC | 744 | 46.8% | [43.2%, 50.4%] | #4 | 0.2951 | +21.0pp | 67.7% |
| #9 · Model Watch · Calibrationgpt-5.6-solearlier version | Sep 28-Oct 4, 2026 UTC | 651 | 46.5% | [42.7%, 50.4%] | #7 | 0.2951 | +21.3pp | 67.9% |
| #10 · Model Watch · Calibrationgpt-5.6-solearlier version | Oct 5-11, 2026 UTC | 734 | 43.5% | [39.9%, 47.1%] | #3 | 0.3059 | +24.7pp | 68.1% |
| #11 · Model Watch · Calibration | Oct 12-18, 2026 UTC | 815 | 46.5% | [43.1%, 49.9%] | #3 | 0.2971 | +21.5pp | 68.0% |
| #12 · Model Watch · Calibration | Oct 19-25, 2026 UTC | 962 | 57.6% | [54.4%, 60.7%] | #3 | 0.2468 | +5.6pp | 63.2% |
| #13 · Model Watch · Calibration | Oct 26-Nov 1, 2026 UTC | 829 | 42.5% | [39.1%, 45.9%] | #2 | 0.2922 | +20.7pp | 63.2% |
| #14 · Model Watch · Calibration | Nov 2-8, 2026 UTC | 807 | 45.6% | [42.2%, 49.0%] | #2 | 0.2804 | +17.4pp | 63.0% |
| #15 · Model Watch · Calibration | Nov 9-15, 2026 UTC | 1,034 | 51.1% | [48.0%, 54.1%] | #1 | 0.2719 | +13.5pp | 64.6% |
Model-line row — version change in this window: ChatGPT 5.6 Sol → GPT-6.1 Sol on 17 Oct 2026 (see the note above).
| Issue (model line) | Window | n | Hit rate | 95% Wilson | Rank | Brier | Gap | Mean stated conf. |
|---|---|---|---|---|---|---|---|---|
| #1 · Model Watch · Calibrationgpt-5.6-solearlier version | Aug 1-31, 2026 UTC | 2,970 | 45.9% | [44.1%, 47.6%] | #4 | 0.3005 | +21.8pp | 67.7% |
| #2 · Model Watch · Calibrationgpt-5.6-solearlier version | Sep 1-30, 2026 UTC | 3,133 | 44.5% | [42.7%, 46.2%] | #6 | 0.3054 | +23.5pp | 68.0% |
| #3 · Model Watch · Calibration | Oct 1-31, 2026 UTC | 3,627 | 48.9% | [47.3%, 50.5%] | #2 | 0.2816 | +16.9pp | 65.8% |
Model-line row — version change in this window: ChatGPT 5.6 Sol → GPT-6.1 Sol on 17 Oct 2026 (see the note above).
| Issue | Window | n | Hit rate | 95% Wilson | Rank | Brier | Gap | Mean stated conf. |
|---|---|---|---|---|---|---|---|---|
| #1 · Model Watch · Calibrationgpt-5.6-solearlier version | Jul 15-Sep 30, 2026 UTC | 9,188 | 44.9% | [43.9%, 45.9%] | #7 | 0.3014 | +22.5pp | 67.4% |
Each figure is the one its issue froze.
Quoted from the issues these figures come from.
Methodology v1.1 (2026-08-10) · hash e66c7e8c864a2233 · Methodology · Benchmarks methodology · Dataset