Benchmarks snapshot — 2026-07-20
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-07-29T12:51:15.544456+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 | 97.9 | 467 / 477 | 239 | 71 | -47.12 | 806.62 | 4.5 |
| 2 | claude-opus-4.8 | 97.9 | 467 / 477 | 301 | 90 | -50.78 | 782.17 | 5.1 |
| 3 | claude-fable-5 | 97.9 | 467 / 477 | 225 | 65 | -46.54 | 823.16 | 4.4 |
| 4 | deepseek-v4-pro | 97.9 | 467 / 477 | 171 | 53 | -26.92 | 873.95 | 2.6 |
| 5 | gemini-3.1-pro | 92.2 | 440 / 477 | 232 | 79 | -36.20 | 847.54 | 2.5 |
| 6 | qwen-3.7-max | 97.3 | 464 / 477 | 305 | 100 | -44.24 | 774.88 | 4.3 |
| 7 | grok-4.5 | 45.7 | 218 / 477 | 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 | 97.9 | 467 / 477 | 199 | 71 | -33.33 | 856.27 | 3.3 |
| 2 | claude-opus-4.8 | 97.9 | 467 / 477 | 230 | 77 | -32.75 | 850.06 | 3.3 |
| 3 | claude-fable-5 | 97.9 | 467 / 477 | 185 | 60 | -33.12 | 857.56 | 3.3 |
| 4 | deepseek-v4-pro | 97.9 | 467 / 477 | 150 | 50 | -17.27 | 898.02 | 1.7 |
| 5 | gemini-3.1-pro | 92.2 | 440 / 477 | 174 | 64 | -15.14 | 883.23 | 1.5 |
| 6 | qwen-3.7-max | 97.3 | 464 / 477 | 245 | 88 | -30.73 | 821.38 | 3.1 |
| 7 | grok-4.5 | 45.7 | 218 / 477 | 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 2026-07-20, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-07-20}
}