Benchmarks snapshot — 2026-08-03
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-08-04T00:20:18.733319+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 | 99.7 | 2949 / 2959 | 1602 | 521 | -298.73 | 698.24 | 29.5 |
| 2 | claude-opus-5 | 99.5 | 2944 / 2959 | 1735 | 561 | -293.77 | 702.28 | 29.1 |
| 3 | claude-fable-5 | 99.6 | 2946 / 2959 | 1460 | 471 | -263.28 | 734.13 | 26.1 |
| 4 | deepseek-v4-pro | 99.7 | 2948 / 2958 | 1141 | 354 | -189.18 | 808.88 | 18.8 |
| 5 | gemini-3.1-pro | 98.4 | 2911 / 2958 | 1501 | 490 | -238.69 | 754.50 | 23.8 |
| 6 | qwen-3.7-max | 99.6 | 2943 / 2956 | 2011 | 652 | -340.80 | 653.06 | 33.9 |
| 7 | grok-4.5 | 86.2 | 2548 / 2955 | 1514 | 466 | -311.59 | 684.32 | 30.8 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.7 | 2949 / 2959 | 1254 | 448 | -209.43 | 786.31 | 20.9 |
| 2 | claude-opus-5 | 99.5 | 2944 / 2959 | 1293 | 459 | -202.77 | 793.57 | 20.3 |
| 3 | claude-fable-5 | 99.6 | 2946 / 2959 | 1142 | 393 | -211.41 | 786.76 | 21.1 |
| 4 | deepseek-v4-pro | 99.7 | 2948 / 2958 | 965 | 313 | -157.67 | 839.41 | 15.8 |
| 5 | gemini-3.1-pro | 98.4 | 2911 / 2958 | 1158 | 411 | -171.71 | 825.93 | 17.2 |
| 6 | qwen-3.7-max | 99.6 | 2943 / 2956 | 1594 | 534 | -259.49 | 736.85 | 25.9 |
| 7 | grok-4.5 | 86.2 | 2548 / 2955 | 1157 | 375 | -238.86 | 757.54 | 23.9 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-08-03, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-08-03}
}