Benchmarks snapshot — 2026-08-08
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-08-09T00:20:21.988735+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 | 3874 / 3884 | 1995 | 636 | -353.02 | 645.35 | 34.1 |
| 2 | claude-opus-5 | 99.6 | 3869 / 3884 | 2045 | 656 | -318.32 | 679.77 | 32.4 |
| 3 | claude-fable-5 | 99.7 | 3871 / 3884 | 1892 | 594 | -312.02 | 685.56 | 31.5 |
| 4 | deepseek-v4-pro | 99.7 | 3873 / 3883 | 1378 | 421 | -232.02 | 766.63 | 23.4 |
| 5 | gemini-3.1-pro | 98.7 | 3834 / 3883 | 1921 | 612 | -287.44 | 708.28 | 28.5 |
| 6 | qwen-3.8-max | 99.6 | 3867 / 3881 | 2486 | 784 | -423.08 | 575.20 | 42.3 |
| 7 | grok-4.5 | 89.5 | 3473 / 3880 | 1912 | 580 | -364.72 | 633.23 | 36.3 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.7 | 3874 / 3884 | 1565 | 553 | -236.33 | 750.53 | 23.8 |
| 2 | claude-opus-5 | 99.6 | 3869 / 3884 | 1540 | 538 | -218.78 | 783.25 | 22.5 |
| 3 | claude-fable-5 | 99.7 | 3871 / 3884 | 1476 | 501 | -249.59 | 752.99 | 25.0 |
| 4 | deepseek-v4-pro | 99.7 | 3873 / 3883 | 1165 | 378 | -198.19 | 802.55 | 19.8 |
| 5 | gemini-3.1-pro | 98.7 | 3834 / 3883 | 1475 | 509 | -207.48 | 785.42 | 21.0 |
| 6 | qwen-3.8-max | 99.6 | 3867 / 3881 | 1982 | 660 | -325.24 | 674.14 | 32.5 |
| 7 | grok-4.5 | 89.5 | 3473 / 3880 | 1457 | 475 | -279.23 | 717.85 | 27.9 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-08-08, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-08-08}
}