Benchmarks snapshot — 2026-07-27
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-07-29T12:50:44.118808+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 | 99.4 | 1602 / 1612 | 856 | 271 | -126.60 | 806.62 | 12.4 |
| 2 | claude-opus-4.8 | 99.4 | 1602 / 1612 | 1095 | 342 | -149.85 | 782.17 | 15.0 |
| 3 | claude-fable-5 | 99.4 | 1602 / 1612 | 818 | 254 | -138.67 | 823.16 | 13.6 |
| 4 | deepseek-v4-pro | 99.4 | 1601 / 1611 | 640 | 194 | -101.22 | 873.95 | 10.1 |
| 5 | gemini-3.1-pro | 97.7 | 1574 / 1611 | 850 | 269 | -103.81 | 847.54 | 9.3 |
| 6 | qwen-3.7-max | 99.2 | 1596 / 1609 | 1109 | 353 | -150.48 | 774.88 | 14.9 |
| 7 | grok-4.5 | 74.7 | 1201 / 1608 | 724 | 218 | -108.19 | 807.20 | 11.0 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.4 | 1602 / 1612 | 678 | 241 | -83.90 | 856.27 | 8.4 |
| 2 | claude-opus-4.8 | 99.4 | 1602 / 1612 | 805 | 286 | -97.58 | 850.06 | 9.8 |
| 3 | claude-fable-5 | 99.4 | 1602 / 1612 | 642 | 227 | -108.03 | 857.56 | 10.8 |
| 4 | deepseek-v4-pro | 99.4 | 1601 / 1611 | 547 | 177 | -79.64 | 898.02 | 8.0 |
| 5 | gemini-3.1-pro | 97.7 | 1574 / 1611 | 651 | 229 | -62.12 | 883.23 | 6.2 |
| 6 | qwen-3.7-max | 99.2 | 1596 / 1609 | 876 | 305 | -111.53 | 821.38 | 11.2 |
| 7 | grok-4.5 | 74.7 | 1201 / 1608 | 547 | 177 | -82.18 | 846.05 | 8.2 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-07-27, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-07-27}
}