Benchmarks snapshot — 2026-09-16
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-09-17T00:20:35.396450+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 | 11811 / 11824 | 6169 | 2131 | -1217.13 | -217.13 | 102.0 |
| 2 | claude-opus-5 | 99.8 | 11805 / 11824 | 5314 | 1861 | -1058.69 | -58.69 | 90.6 |
| 3 | claude-fable-5 | 99.8 | 11804 / 11824 | 5769 | 2010 | -1115.20 | -115.20 | 89.7 |
| 4 | deepseek-v4-pro | 99.9 | 11806 / 11823 | 5557 | 1994 | -991.44 | 8.56 | 89.4 |
| 5 | gemini-3.1-pro | 99.6 | 11769 / 11822 | 6240 | 2228 | -811.92 | 188.08 | 78.4 |
| 6 | qwen-3.8-max | 99.1 | 11708 / 11816 | 6582 | 2250 | -1115.99 | -115.99 | 108.8 |
| 7 | grok-4.6 | 96.5 | 11400 / 11815 | 5305 | 1751 | -1165.49 | -165.49 | 107.2 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.9 | 11811 / 11824 | 4889 | 1728 | -730.06 | 269.94 | 73.0 |
| 2 | claude-opus-5 | 99.8 | 11805 / 11824 | 4107 | 1484 | -498.64 | 501.36 | 49.9 |
| 3 | claude-fable-5 | 99.8 | 11804 / 11824 | 4546 | 1611 | -547.05 | 452.95 | 54.7 |
| 4 | deepseek-v4-pro | 99.9 | 11806 / 11823 | 4660 | 1694 | -651.19 | 348.81 | 65.1 |
| 5 | gemini-3.1-pro | 99.6 | 11769 / 11822 | 4813 | 1762 | -518.59 | 481.41 | 51.9 |
| 6 | qwen-3.8-max | 99.1 | 11708 / 11816 | 5420 | 1930 | -726.97 | 273.03 | 72.7 |
| 7 | grok-4.6 | 96.5 | 11400 / 11815 | 4211 | 1433 | -742.68 | 257.32 | 74.3 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-09-16, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-09-16}
}