Benchmarks snapshot — 2026-08-11
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-08-12T00:20:25.518607+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 | 99.8 | 4454 / 4464 | 2311 | 731 | -385.72 | 613.14 | 39.0 |
| 2 | claude-opus-5 | 99.7 | 4449 / 4464 | 2268 | 721 | -344.47 | 655.29 | 35.5 |
| 3 | claude-fable-5 | 99.7 | 4451 / 4464 | 2162 | 671 | -340.33 | 660.69 | 34.6 |
| 4 | deepseek-v4-pro | 99.8 | 4453 / 4463 | 1603 | 477 | -259.04 | 739.03 | 26.4 |
| 5 | gemini-3.1-pro | 98.9 | 4413 / 4462 | 2205 | 695 | -331.17 | 671.75 | 33.2 |
| 6 | qwen-3.8-max | 99.7 | 4441 / 4456 | 2783 | 885 | -445.18 | 556.45 | 44.7 |
| 7 | grok-4.5 | 90.9 | 4048 / 4455 | 2236 | 680 | -398.47 | 602.40 | 40.7 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.8 | 4454 / 4464 | 1821 | 630 | -274.84 | 728.28 | 27.5 |
| 2 | claude-opus-5 | 99.7 | 4449 / 4464 | 1712 | 596 | -244.41 | 764.43 | 24.4 |
| 3 | claude-fable-5 | 99.7 | 4451 / 4464 | 1688 | 569 | -272.42 | 732.71 | 27.2 |
| 4 | deepseek-v4-pro | 99.8 | 4453 / 4463 | 1361 | 435 | -225.81 | 776.95 | 22.6 |
| 5 | gemini-3.1-pro | 98.9 | 4413 / 4462 | 1689 | 579 | -243.08 | 758.88 | 24.3 |
| 6 | qwen-3.8-max | 99.7 | 4441 / 4456 | 2231 | 746 | -340.01 | 662.13 | 34.0 |
| 7 | grok-4.5 | 90.9 | 4048 / 4455 | 1709 | 555 | -311.01 | 696.44 | 31.1 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-08-11, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-08-11}
}