Benchmarks snapshot — 2026-09-25
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-09-26T00:20:38.682554+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 | 13701 / 13714 | 7381 | 2733 | 391.28 | 1391.28 | 104.7 |
| 2 | claude-opus-5 | 99.9 | 13695 / 13714 | 6435 | 2423 | 272.30 | 1272.30 | 92.9 |
| 3 | claude-fable-5 | 99.8 | 13693 / 13714 | 7025 | 2662 | 812.72 | 1812.72 | 90.8 |
| 4 | deepseek-v4-pro | 99.7 | 13676 / 13713 | 6904 | 2632 | 122.07 | 1122.07 | 92.0 |
| 5 | gemini-3.1-pro | 99.6 | 13659 / 13712 | 7493 | 2836 | -357.81 | 642.19 | 80.2 |
| 6 | qwen-3.8-max | 99.1 | 13581 / 13706 | 7752 | 2784 | -761.33 | 238.67 | 111.5 |
| 7 | grok-4.6 | 97.0 | 13287 / 13705 | 6201 | 2181 | -315.04 | 684.96 | 109.1 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.9 | 13701 / 13714 | 5755 | 2136 | -601.41 | 398.59 | 75.4 |
| 2 | claude-opus-5 | 99.9 | 13695 / 13714 | 4892 | 1858 | -392.05 | 607.95 | 51.7 |
| 3 | claude-fable-5 | 99.8 | 13693 / 13714 | 5436 | 2025 | -449.19 | 550.81 | 55.8 |
| 4 | deepseek-v4-pro | 99.7 | 13676 / 13713 | 5720 | 2161 | -608.75 | 391.25 | 67.3 |
| 5 | gemini-3.1-pro | 99.6 | 13659 / 13712 | 5734 | 2227 | -349.41 | 650.59 | 52.9 |
| 6 | qwen-3.8-max | 99.1 | 13581 / 13706 | 6369 | 2361 | -665.00 | 335.00 | 75.6 |
| 7 | grok-4.6 | 97.0 | 13287 / 13705 | 4899 | 1749 | -724.53 | 275.47 | 77.3 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-09-25, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-09-25}
}