Benchmarks snapshot — 2026-07-25
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-07-29T12:50:53.505891+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 | 99.2 | 1206 / 1216 | 652 | 206 | -97.11 | 806.62 | 9.5 |
| 2 | claude-opus-4.8 | 99.2 | 1206 / 1216 | 806 | 248 | -103.50 | 782.17 | 10.3 |
| 3 | claude-fable-5 | 99.2 | 1206 / 1216 | 573 | 178 | -96.52 | 823.16 | 9.4 |
| 4 | deepseek-v4-pro | 99.2 | 1206 / 1216 | 504 | 164 | -69.92 | 873.95 | 6.9 |
| 5 | gemini-3.1-pro | 97.0 | 1179 / 1216 | 627 | 201 | -81.30 | 847.54 | 7.0 |
| 6 | qwen-3.7-max | 98.9 | 1201 / 1214 | 830 | 263 | -107.56 | 774.88 | 10.6 |
| 7 | grok-4.5 | 66.5 | 807 / 1214 | 496 | 149 | -70.74 | 807.20 | 7.3 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.2 | 1206 / 1216 | 512 | 184 | -62.40 | 856.27 | 6.2 |
| 2 | claude-opus-4.8 | 99.2 | 1206 / 1216 | 593 | 202 | -66.92 | 850.06 | 6.7 |
| 3 | claude-fable-5 | 99.2 | 1206 / 1216 | 449 | 158 | -73.42 | 857.56 | 7.3 |
| 4 | deepseek-v4-pro | 99.2 | 1206 / 1216 | 423 | 145 | -52.75 | 898.02 | 5.3 |
| 5 | gemini-3.1-pro | 97.0 | 1179 / 1216 | 474 | 166 | -52.94 | 883.23 | 5.3 |
| 6 | qwen-3.7-max | 98.9 | 1201 / 1214 | 653 | 231 | -76.27 | 821.38 | 7.6 |
| 7 | grok-4.5 | 66.5 | 807 / 1214 | 371 | 121 | -55.69 | 846.05 | 5.6 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-07-25, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-07-25}
}