Benchmarks snapshot — 2026-09-04
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-09-05T00:20:26.778620+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 | 99.9 | 9294 / 9304 | 4752 | 1628 | -472.05 | 527.95 | 58.9 |
| 2 | claude-opus-5 | 99.8 | 9285 / 9304 | 4228 | 1491 | -381.20 | 618.80 | 48.4 |
| 3 | claude-fable-5 | 99.8 | 9284 / 9304 | 4476 | 1566 | -276.94 | 723.06 | 42.6 |
| 4 | deepseek-v4-pro | 99.8 | 9286 / 9303 | 4070 | 1447 | -391.81 | 608.19 | 51.6 |
| 5 | gemini-3.1-pro | 99.4 | 9249 / 9302 | 4849 | 1726 | -381.71 | 618.29 | 41.0 |
| 6 | qwen-3.8-max | 98.9 | 9198 / 9296 | 5182 | 1762 | -637.68 | 362.32 | 69.7 |
| 7 | grok-4.6 | 95.5 | 8880 / 9295 | 4285 | 1399 | -653.38 | 346.62 | 69.7 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.9 | 9294 / 9304 | 3829 | 1379 | -430.95 | 569.05 | 43.1 |
| 2 | claude-opus-5 | 99.8 | 9285 / 9304 | 3307 | 1229 | -254.91 | 745.09 | 30.1 |
| 3 | claude-fable-5 | 99.8 | 9284 / 9304 | 3591 | 1312 | -248.61 | 751.39 | 35.3 |
| 4 | deepseek-v4-pro | 99.8 | 9286 / 9303 | 3513 | 1282 | -400.79 | 599.21 | 40.1 |
| 5 | gemini-3.1-pro | 99.4 | 9249 / 9302 | 3759 | 1402 | -269.85 | 730.15 | 31.7 |
| 6 | qwen-3.8-max | 98.9 | 9198 / 9296 | 4291 | 1541 | -427.90 | 572.10 | 42.8 |
| 7 | grok-4.6 | 95.5 | 8880 / 9295 | 3419 | 1172 | -505.67 | 494.33 | 50.6 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-09-04, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-09-04}
}