Benchmarks snapshot — 2026-09-15
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-09-16T00:20:27.529883+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 | 11601 / 11614 | 6028 | 2095 | -1296.79 | -296.79 | 91.4 |
| 2 | claude-opus-5 | 99.8 | 11595 / 11614 | 5239 | 1844 | -1147.69 | -147.69 | 86.3 |
| 3 | claude-fable-5 | 99.8 | 11594 / 11614 | 5687 | 1989 | -1240.80 | -240.80 | 84.8 |
| 4 | deepseek-v4-pro | 99.9 | 11596 / 11613 | 5421 | 1952 | -1058.98 | -58.98 | 82.3 |
| 5 | gemini-3.1-pro | 99.5 | 11559 / 11612 | 6110 | 2193 | -786.30 | 213.70 | 71.7 |
| 6 | qwen-3.8-max | 99.1 | 11501 / 11606 | 6479 | 2226 | -1110.24 | -110.24 | 105.2 |
| 7 | grok-4.6 | 96.4 | 11190 / 11605 | 5214 | 1727 | -1221.06 | -221.06 | 104.6 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.9 | 11601 / 11614 | 4785 | 1708 | -690.71 | 309.29 | 69.1 |
| 2 | claude-opus-5 | 99.8 | 11595 / 11614 | 4043 | 1473 | -464.82 | 535.18 | 46.5 |
| 3 | claude-fable-5 | 99.8 | 11594 / 11614 | 4474 | 1595 | -516.62 | 483.38 | 51.7 |
| 4 | deepseek-v4-pro | 99.9 | 11596 / 11613 | 4547 | 1658 | -620.87 | 379.13 | 62.1 |
| 5 | gemini-3.1-pro | 99.5 | 11559 / 11612 | 4715 | 1736 | -487.50 | 512.50 | 48.8 |
| 6 | qwen-3.8-max | 99.1 | 11501 / 11606 | 5327 | 1909 | -693.84 | 306.16 | 69.4 |
| 7 | grok-4.6 | 96.4 | 11190 / 11605 | 4134 | 1418 | -713.91 | 286.09 | 71.4 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-09-15, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-09-15}
}