Benchmarks snapshot — 2026-07-19
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-07-29T12:51:19.704135+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 | 100.0 | 369 / 369 | 178 | 55 | -24.94 | 806.62 | 2.3 |
| 2 | claude-opus-4.8 | 100.0 | 369 / 369 | 239 | 72 | -28.85 | 782.17 | 2.9 |
| 3 | claude-fable-5 | 100.0 | 369 / 369 | 169 | 48 | -27.16 | 823.16 | 2.4 |
| 4 | deepseek-v4-pro | 100.0 | 369 / 369 | 122 | 36 | -14.61 | 873.95 | 1.4 |
| 5 | gemini-3.1-pro | 92.7 | 342 / 369 | 177 | 56 | -29.18 | 847.54 | 1.8 |
| 6 | qwen-3.7-max | 99.7 | 368 / 369 | 236 | 77 | -27.12 | 774.88 | 2.6 |
| 7 | grok-4.5 | 59.1 | 218 / 369 | 139 | 39 | -24.66 | 807.20 | 2.7 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 100.0 | 369 / 369 | 145 | 56 | -14.00 | 856.27 | 1.6 |
| 2 | claude-opus-4.8 | 100.0 | 369 / 369 | 181 | 60 | -19.11 | 850.06 | 1.9 |
| 3 | claude-fable-5 | 100.0 | 369 / 369 | 138 | 45 | -20.68 | 857.56 | 2.1 |
| 4 | deepseek-v4-pro | 100.0 | 369 / 369 | 106 | 34 | -8.22 | 898.02 | 0.9 |
| 5 | gemini-3.1-pro | 92.7 | 342 / 369 | 131 | 44 | -13.73 | 883.23 | 1.4 |
| 6 | qwen-3.7-max | 99.7 | 368 / 369 | 189 | 67 | -18.11 | 821.38 | 1.8 |
| 7 | grok-4.5 | 59.1 | 218 / 369 | 113 | 39 | -21.42 | 846.05 | 2.3 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-07-19, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-07-19}
}