Benchmarks snapshot — 2026-09-17
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-09-18T00:20:34.477325+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 | 12021 / 12034 | 6265 | 2164 | -1107.66 | -107.66 | 104.7 |
| 2 | claude-opus-5 | 99.8 | 12015 / 12034 | 5422 | 1902 | -961.66 | 38.34 | 92.9 |
| 3 | claude-fable-5 | 99.8 | 12014 / 12034 | 5900 | 2067 | -949.42 | 50.58 | 90.8 |
| 4 | deepseek-v4-pro | 99.9 | 12016 / 12033 | 5660 | 2034 | -898.89 | 101.11 | 92.0 |
| 5 | gemini-3.1-pro | 99.6 | 11979 / 12032 | 6346 | 2274 | -796.67 | 203.33 | 80.2 |
| 6 | qwen-3.8-max | 99.1 | 11917 / 12026 | 6682 | 2290 | -1107.72 | -107.72 | 111.5 |
| 7 | grok-4.6 | 96.5 | 11610 / 12025 | 5370 | 1772 | -1103.78 | -103.78 | 109.1 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.9 | 12021 / 12034 | 4961 | 1752 | -753.90 | 246.10 | 75.4 |
| 2 | claude-opus-5 | 99.8 | 12015 / 12034 | 4190 | 1518 | -517.44 | 482.56 | 51.7 |
| 3 | claude-fable-5 | 99.8 | 12014 / 12034 | 4644 | 1654 | -558.32 | 441.68 | 55.8 |
| 4 | deepseek-v4-pro | 99.9 | 12016 / 12033 | 4752 | 1728 | -673.38 | 326.62 | 67.3 |
| 5 | gemini-3.1-pro | 99.6 | 11979 / 12032 | 4892 | 1798 | -528.86 | 471.14 | 52.9 |
| 6 | qwen-3.8-max | 99.1 | 11917 / 12026 | 5501 | 1959 | -755.57 | 244.43 | 75.6 |
| 7 | grok-4.6 | 96.5 | 11610 / 12025 | 4264 | 1450 | -760.43 | 239.57 | 76.0 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-09-17, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-09-17}
}