Benchmarks snapshot — 2026-07-29
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-07-29T12:50:34.338303+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 | 99.5 | 1907 / 1917 | 1027 | 315 | -193.38 | 806.62 | 19.1 |
| 2 | claude-opus-4.8 | 99.5 | 1907 / 1917 | 1308 | 408 | -217.83 | 782.17 | 21.8 |
| 3 | claude-fable-5 | 99.5 | 1907 / 1917 | 967 | 300 | -176.84 | 823.16 | 17.4 |
| 4 | deepseek-v4-pro | 99.5 | 1906 / 1916 | 778 | 234 | -126.05 | 873.95 | 12.5 |
| 5 | gemini-3.1-pro | 97.8 | 1874 / 1916 | 982 | 308 | -152.46 | 847.54 | 14.2 |
| 6 | qwen-3.7-max | 99.3 | 1901 / 1914 | 1306 | 406 | -225.12 | 774.88 | 22.4 |
| 7 | grok-4.5 | 78.7 | 1506 / 1913 | 923 | 275 | -192.80 | 807.20 | 19.5 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.5 | 1907 / 1917 | 829 | 286 | -143.73 | 856.27 | 14.4 |
| 2 | claude-opus-4.8 | 99.5 | 1907 / 1917 | 979 | 349 | -149.94 | 850.06 | 15.0 |
| 3 | claude-fable-5 | 99.5 | 1907 / 1917 | 769 | 271 | -142.44 | 857.56 | 14.2 |
| 4 | deepseek-v4-pro | 99.5 | 1906 / 1916 | 664 | 215 | -101.98 | 898.02 | 10.2 |
| 5 | gemini-3.1-pro | 97.8 | 1874 / 1916 | 773 | 266 | -116.77 | 883.23 | 11.7 |
| 6 | qwen-3.7-max | 99.3 | 1901 / 1914 | 1053 | 352 | -178.62 | 821.38 | 17.9 |
| 7 | grok-4.5 | 78.7 | 1506 / 1913 | 716 | 230 | -153.95 | 846.05 | 15.4 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-07-29, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-07-29}
}