Benchmarks snapshot — 2026-09-11
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-09-12T00:20:29.761371+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 | 10761 / 10774 | 5563 | 1937 | -640.19 | 359.81 | 58.9 |
| 2 | claude-opus-5 | 99.8 | 10755 / 10774 | 4882 | 1717 | -581.00 | 419.00 | 59.2 |
| 3 | claude-fable-5 | 99.8 | 10754 / 10774 | 5235 | 1835 | -472.47 | 527.53 | 42.6 |
| 4 | deepseek-v4-pro | 99.8 | 10756 / 10773 | 4951 | 1787 | -561.17 | 438.83 | 55.3 |
| 5 | gemini-3.1-pro | 99.5 | 10719 / 10772 | 5655 | 2028 | -579.14 | 420.86 | 54.2 |
| 6 | qwen-3.8-max | 99.1 | 10665 / 10766 | 6035 | 2064 | -872.52 | 127.48 | 86.6 |
| 7 | grok-4.6 | 96.1 | 10350 / 10765 | 4859 | 1598 | -845.11 | 154.89 | 82.2 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.9 | 10761 / 10774 | 4440 | 1594 | -536.98 | 463.02 | 53.7 |
| 2 | claude-opus-5 | 99.8 | 10755 / 10774 | 3773 | 1376 | -364.61 | 635.39 | 36.5 |
| 3 | claude-fable-5 | 99.8 | 10754 / 10774 | 4146 | 1481 | -384.93 | 615.07 | 38.5 |
| 4 | deepseek-v4-pro | 99.8 | 10756 / 10773 | 4184 | 1518 | -521.49 | 478.51 | 52.1 |
| 5 | gemini-3.1-pro | 99.5 | 10719 / 10772 | 4365 | 1619 | -347.95 | 652.05 | 34.8 |
| 6 | qwen-3.8-max | 99.1 | 10665 / 10766 | 4960 | 1774 | -592.17 | 407.83 | 59.2 |
| 7 | grok-4.6 | 96.1 | 10350 / 10765 | 3862 | 1315 | -638.08 | 361.92 | 63.8 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-09-11, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-09-11}
}