Benchmarks snapshot — 2026-08-04
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-08-05T00:20:23.010168+00:00. 7 models · 5 instruments.
Official leaderboard — per-forecast
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.7 | 3139 / 3149 | 1650 | 530 | -312.49 | 687.21 | 30.7 |
| 2 | claude-opus-5 | 99.5 | 3134 / 3149 | 1770 | 569 | -301.41 | 698.64 | 29.9 |
| 3 | claude-fable-5 | 99.6 | 3136 / 3149 | 1530 | 493 | -272.14 | 727.00 | 27.2 |
| 4 | deepseek-v4-pro | 99.7 | 3138 / 3148 | 1169 | 360 | -196.95 | 801.03 | 19.6 |
| 5 | gemini-3.1-pro | 98.5 | 3101 / 3148 | 1562 | 504 | -258.23 | 741.30 | 25.6 |
| 6 | qwen-3.7-max | 99.6 | 3133 / 3146 | 2095 | 670 | -365.43 | 631.99 | 36.3 |
| 7 | grok-4.5 | 87.1 | 2738 / 3145 | 1558 | 477 | -322.69 | 677.75 | 31.8 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.7 | 3139 / 3149 | 1291 | 454 | -219.54 | 774.34 | 22.0 |
| 2 | claude-opus-5 | 99.5 | 3134 / 3149 | 1319 | 464 | -207.50 | 790.87 | 20.7 |
| 3 | claude-fable-5 | 99.6 | 3136 / 3149 | 1198 | 411 | -220.39 | 781.42 | 22.0 |
| 4 | deepseek-v4-pro | 99.7 | 3138 / 3148 | 990 | 317 | -165.96 | 830.82 | 16.6 |
| 5 | gemini-3.1-pro | 98.5 | 3101 / 3148 | 1203 | 420 | -186.12 | 811.91 | 18.6 |
| 6 | qwen-3.7-max | 99.6 | 3133 / 3146 | 1662 | 551 | -278.94 | 715.99 | 27.9 |
| 7 | grok-4.5 | 87.1 | 2738 / 3145 | 1188 | 384 | -243.77 | 751.70 | 24.4 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-08-04, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-08-04}
}