Benchmarks snapshot — 2026-09-07
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-09-08T00:20:30.998221+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 | 9924 / 9934 | 5063 | 1751 | -334.85 | 665.15 | 58.9 |
| 2 | claude-opus-5 | 99.8 | 9915 / 9934 | 4480 | 1589 | -264.16 | 735.84 | 48.4 |
| 3 | claude-fable-5 | 99.8 | 9914 / 9934 | 4768 | 1684 | -122.32 | 877.68 | 42.6 |
| 4 | deepseek-v4-pro | 99.8 | 9916 / 9933 | 4392 | 1573 | -299.21 | 700.79 | 51.6 |
| 5 | gemini-3.1-pro | 99.5 | 9879 / 9932 | 5181 | 1850 | -372.87 | 627.13 | 41.0 |
| 6 | qwen-3.8-max | 99.0 | 9828 / 9926 | 5504 | 1880 | -617.21 | 382.79 | 69.7 |
| 7 | grok-4.6 | 95.8 | 9510 / 9925 | 4468 | 1462 | -592.09 | 407.91 | 69.7 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.9 | 9924 / 9934 | 4073 | 1456 | -444.21 | 555.79 | 44.4 |
| 2 | claude-opus-5 | 99.8 | 9915 / 9934 | 3498 | 1288 | -246.40 | 753.60 | 30.1 |
| 3 | claude-fable-5 | 99.8 | 9914 / 9934 | 3813 | 1377 | -259.32 | 740.68 | 35.3 |
| 4 | deepseek-v4-pro | 99.8 | 9916 / 9933 | 3777 | 1370 | -412.30 | 587.70 | 41.2 |
| 5 | gemini-3.1-pro | 99.5 | 9879 / 9932 | 4017 | 1485 | -281.25 | 718.75 | 31.7 |
| 6 | qwen-3.8-max | 99.0 | 9828 / 9926 | 4568 | 1636 | -439.81 | 560.19 | 44.0 |
| 7 | grok-4.6 | 95.8 | 9510 / 9925 | 3571 | 1213 | -519.99 | 480.01 | 52.0 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-09-07, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-09-07}
}