Benchmarks snapshot — 2026-07-31
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-08-01T00:20:18.411413+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 | 99.6 | 2359 / 2369 | 1283 | 406 | -239.42 | 759.12 | 24.4 |
| 2 | claude-opus-5 | 99.4 | 2354 / 2369 | 1516 | 480 | -259.69 | 738.89 | 26.4 |
| 3 | claude-fable-5 | 99.5 | 2356 / 2369 | 1183 | 375 | -220.48 | 778.17 | 21.6 |
| 4 | deepseek-v4-pro | 99.6 | 2358 / 2368 | 921 | 282 | -154.91 | 844.26 | 15.5 |
| 5 | gemini-3.1-pro | 98.0 | 2321 / 2368 | 1195 | 386 | -189.93 | 808.13 | 19.0 |
| 6 | qwen-3.7-max | 99.5 | 2353 / 2366 | 1618 | 513 | -278.52 | 720.22 | 28.5 |
| 7 | grok-4.5 | 82.8 | 1958 / 2365 | 1167 | 360 | -244.03 | 754.76 | 24.9 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.6 | 2359 / 2369 | 1019 | 355 | -185.28 | 817.54 | 18.5 |
| 2 | claude-opus-5 | 99.4 | 2354 / 2369 | 1126 | 398 | -184.99 | 817.87 | 18.5 |
| 3 | claude-fable-5 | 99.5 | 2356 / 2369 | 935 | 319 | -176.23 | 817.87 | 17.6 |
| 4 | deepseek-v4-pro | 99.6 | 2358 / 2368 | 783 | 250 | -131.67 | 866.62 | 13.2 |
| 5 | gemini-3.1-pro | 98.0 | 2321 / 2368 | 930 | 323 | -144.33 | 853.26 | 14.4 |
| 6 | qwen-3.7-max | 99.5 | 2353 / 2366 | 1290 | 433 | -227.51 | 777.44 | 22.8 |
| 7 | grok-4.5 | 82.8 | 1958 / 2365 | 892 | 285 | -202.87 | 800.34 | 20.3 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-07-31, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-07-31}
}