Benchmarks snapshot — 2026-07-26
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-07-29T12:50:48.884369+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 | 99.3 | 1394 / 1404 | 746 | 241 | -100.07 | 806.62 | 9.8 |
| 2 | claude-opus-4.8 | 99.3 | 1394 / 1404 | 956 | 303 | -98.72 | 782.17 | 10.3 |
| 3 | claude-fable-5 | 99.3 | 1394 / 1404 | 705 | 223 | -98.96 | 823.16 | 9.6 |
| 4 | deepseek-v4-pro | 99.3 | 1394 / 1404 | 558 | 176 | -78.53 | 873.95 | 7.8 |
| 5 | gemini-3.1-pro | 97.4 | 1367 / 1404 | 735 | 235 | -87.96 | 847.54 | 7.7 |
| 6 | qwen-3.7-max | 99.1 | 1389 / 1402 | 959 | 308 | -110.99 | 774.88 | 11.0 |
| 7 | grok-4.5 | 70.9 | 994 / 1401 | 601 | 184 | -73.14 | 807.20 | 7.5 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.3 | 1394 / 1404 | 586 | 212 | -62.98 | 856.27 | 6.3 |
| 2 | claude-opus-4.8 | 99.3 | 1394 / 1404 | 698 | 249 | -60.91 | 850.06 | 6.7 |
| 3 | claude-fable-5 | 99.3 | 1394 / 1404 | 546 | 197 | -74.52 | 857.56 | 7.5 |
| 4 | deepseek-v4-pro | 99.3 | 1394 / 1404 | 474 | 158 | -61.04 | 898.02 | 6.1 |
| 5 | gemini-3.1-pro | 97.4 | 1367 / 1404 | 557 | 198 | -57.05 | 883.23 | 5.7 |
| 6 | qwen-3.7-max | 99.1 | 1389 / 1402 | 753 | 265 | -78.86 | 821.38 | 7.9 |
| 7 | grok-4.5 | 70.9 | 994 / 1401 | 452 | 146 | -56.91 | 846.05 | 5.7 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-07-26, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-07-26}
}