Benchmarks snapshot — 2026-07-23
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-07-29T12:51:02.613528+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 | 98.8 | 826 / 836 | 446 | 144 | -73.63 | 806.62 | 7.1 |
| 2 | claude-opus-4.8 | 98.8 | 826 / 836 | 544 | 175 | -73.76 | 782.17 | 7.4 |
| 3 | claude-fable-5 | 98.8 | 826 / 836 | 414 | 133 | -70.10 | 823.16 | 6.7 |
| 4 | deepseek-v4-pro | 98.8 | 826 / 836 | 341 | 111 | -51.97 | 873.95 | 5.1 |
| 5 | gemini-3.1-pro | 95.6 | 799 / 836 | 425 | 145 | -54.36 | 847.54 | 4.4 |
| 6 | qwen-3.7-max | 98.4 | 822 / 835 | 565 | 183 | -83.97 | 774.88 | 8.3 |
| 7 | grok-4.5 | 51.3 | 428 / 835 | 247 | 73 | -47.56 | 807.20 | 5.0 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 98.8 | 826 / 836 | 352 | 135 | -48.16 | 856.27 | 4.8 |
| 2 | claude-opus-4.8 | 98.8 | 826 / 836 | 404 | 146 | -47.12 | 850.06 | 4.7 |
| 3 | claude-fable-5 | 98.8 | 826 / 836 | 326 | 117 | -53.24 | 857.56 | 5.3 |
| 4 | deepseek-v4-pro | 98.8 | 826 / 836 | 286 | 98 | -39.61 | 898.02 | 4.0 |
| 5 | gemini-3.1-pro | 95.6 | 799 / 836 | 318 | 122 | -30.72 | 883.23 | 3.1 |
| 6 | qwen-3.7-max | 98.4 | 822 / 835 | 444 | 168 | -59.71 | 821.38 | 6.0 |
| 7 | grok-4.5 | 51.3 | 428 / 835 | 190 | 67 | -41.96 | 846.05 | 4.2 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-07-23, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-07-23}
}