Benchmarks snapshot — 2026-08-13
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-08-14T00:20:23.562547+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 | 99.8 | 4834 / 4844 | 2493 | 789 | -412.85 | 585.53 | 42.2 |
| 2 | claude-opus-5 | 99.7 | 4829 / 4844 | 2387 | 757 | -364.64 | 633.81 | 38.0 |
| 3 | claude-fable-5 | 99.7 | 4831 / 4844 | 2319 | 716 | -371.10 | 627.60 | 37.7 |
| 4 | deepseek-v4-pro | 99.8 | 4832 / 4843 | 1737 | 516 | -286.95 | 711.82 | 29.0 |
| 5 | gemini-3.1-pro | 99.0 | 4793 / 4842 | 2391 | 762 | -350.20 | 649.20 | 35.5 |
| 6 | qwen-3.8-max | 99.7 | 4821 / 4836 | 2951 | 934 | -473.07 | 525.24 | 47.5 |
| 7 | grok-4.5 | 91.6 | 4428 / 4835 | 2422 | 740 | -423.31 | 575.32 | 43.6 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.8 | 4834 / 4844 | 1962 | 670 | -300.81 | 705.90 | 30.1 |
| 2 | claude-opus-5 | 99.7 | 4829 / 4844 | 1807 | 626 | -267.19 | 745.77 | 26.7 |
| 3 | claude-fable-5 | 99.7 | 4831 / 4844 | 1814 | 604 | -302.47 | 701.56 | 30.2 |
| 4 | deepseek-v4-pro | 99.8 | 4832 / 4843 | 1477 | 466 | -252.01 | 750.08 | 25.2 |
| 5 | gemini-3.1-pro | 99.0 | 4793 / 4842 | 1827 | 622 | -267.46 | 736.39 | 26.7 |
| 6 | qwen-3.8-max | 99.7 | 4821 / 4836 | 2370 | 788 | -365.80 | 634.54 | 36.6 |
| 7 | grok-4.5 | 91.6 | 4428 / 4835 | 1850 | 598 | -334.79 | 675.76 | 33.5 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-08-13, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-08-13}
}