Benchmarks snapshot — 2026-09-13
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-09-14T00:20:29.111782+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 | 99.9 | 11181 / 11194 | 5738 | 1988 | -852.09 | 147.91 | 61.9 |
| 2 | claude-opus-5 | 99.8 | 11175 / 11194 | 5012 | 1758 | -782.65 | 217.35 | 61.5 |
| 3 | claude-fable-5 | 99.8 | 11174 / 11194 | 5391 | 1880 | -728.29 | 271.71 | 46.1 |
| 4 | deepseek-v4-pro | 99.8 | 11176 / 11193 | 5115 | 1834 | -753.67 | 246.33 | 55.3 |
| 5 | gemini-3.1-pro | 99.5 | 11139 / 11192 | 5830 | 2082 | -652.72 | 347.28 | 58.6 |
| 6 | qwen-3.8-max | 99.1 | 11082 / 11186 | 6206 | 2118 | -960.11 | 39.89 | 89.3 |
| 7 | grok-4.6 | 96.3 | 10770 / 11185 | 4983 | 1636 | -997.19 | 2.81 | 85.1 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.9 | 11181 / 11194 | 4576 | 1634 | -562.63 | 437.37 | 56.3 |
| 2 | claude-opus-5 | 99.8 | 11175 / 11194 | 3876 | 1408 | -381.70 | 618.30 | 38.2 |
| 3 | claude-fable-5 | 99.8 | 11174 / 11194 | 4266 | 1517 | -407.92 | 592.08 | 40.8 |
| 4 | deepseek-v4-pro | 99.8 | 11176 / 11193 | 4317 | 1562 | -543.94 | 456.06 | 54.4 |
| 5 | gemini-3.1-pro | 99.5 | 11139 / 11192 | 4497 | 1660 | -373.84 | 626.16 | 37.4 |
| 6 | qwen-3.8-max | 99.1 | 11082 / 11186 | 5104 | 1820 | -614.86 | 385.14 | 61.5 |
| 7 | grok-4.6 | 96.3 | 10770 / 11185 | 3964 | 1347 | -659.50 | 340.50 | 66.0 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-09-13, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-09-13}
}