Benchmarks snapshot — 2026-08-07
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-08-08T00:20:19.947317+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 | 3684 / 3694 | 1902 | 606 | -340.01 | 660.85 | 33.8 |
| 2 | claude-opus-5 | 99.6 | 3679 / 3694 | 1957 | 626 | -311.81 | 689.19 | 32.4 |
| 3 | claude-fable-5 | 99.6 | 3681 / 3694 | 1784 | 559 | -305.78 | 694.72 | 31.2 |
| 4 | deepseek-v4-pro | 99.7 | 3683 / 3693 | 1327 | 405 | -227.25 | 772.81 | 22.5 |
| 5 | gemini-3.1-pro | 98.7 | 3644 / 3693 | 1819 | 577 | -288.55 | 713.59 | 28.5 |
| 6 | qwen-3.8-max | 99.6 | 3677 / 3691 | 2373 | 751 | -409.05 | 590.49 | 40.7 |
| 7 | grok-4.5 | 89.0 | 3283 / 3690 | 1824 | 552 | -359.35 | 641.94 | 36.0 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.7 | 3684 / 3694 | 1493 | 526 | -238.17 | 760.00 | 23.8 |
| 2 | claude-opus-5 | 99.6 | 3679 / 3694 | 1472 | 511 | -225.23 | 788.88 | 22.5 |
| 3 | claude-fable-5 | 99.6 | 3681 / 3694 | 1395 | 471 | -248.02 | 759.00 | 24.8 |
| 4 | deepseek-v4-pro | 99.7 | 3683 / 3693 | 1126 | 362 | -188.72 | 808.41 | 18.9 |
| 5 | gemini-3.1-pro | 98.7 | 3644 / 3693 | 1400 | 482 | -210.29 | 788.54 | 21.0 |
| 6 | qwen-3.8-max | 99.6 | 3677 / 3691 | 1895 | 629 | -313.43 | 683.23 | 31.3 |
| 7 | grok-4.5 | 89.0 | 3283 / 3690 | 1392 | 450 | -278.48 | 723.82 | 27.8 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-08-07, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-08-07}
}