Benchmarks snapshot — 2026-09-30
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-10-01T00:20:41.832263+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 | 14751 / 14764 | 7855 | 2894 | 40.37 | 1040.37 | 104.7 |
| 2 | claude-opus-5 | 99.9 | 14745 / 14764 | 6814 | 2557 | -59.61 | 940.39 | 92.9 |
| 3 | claude-fable-5 | 99.9 | 14743 / 14764 | 7470 | 2818 | 476.16 | 1476.16 | 90.8 |
| 4 | deepseek-v4-pro | 99.7 | 14726 / 14763 | 7394 | 2804 | -232.98 | 767.02 | 92.0 |
| 5 | gemini-3.1-pro | 99.6 | 14709 / 14762 | 8016 | 3017 | -591.95 | 408.05 | 80.2 |
| 6 | qwen-3.8-max | 99.1 | 14627 / 14756 | 8249 | 2946 | -1044.00 | -44.00 | 111.5 |
| 7 | grok-4.6 | 97.1 | 14332 / 14755 | 6517 | 2296 | -612.37 | 387.63 | 109.1 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.9 | 14751 / 14764 | 6122 | 2235 | -685.10 | 314.90 | 75.4 |
| 2 | claude-opus-5 | 99.9 | 14745 / 14764 | 5198 | 1946 | -481.72 | 518.28 | 51.7 |
| 3 | claude-fable-5 | 99.9 | 14743 / 14764 | 5786 | 2124 | -533.68 | 466.32 | 55.8 |
| 4 | deepseek-v4-pro | 99.7 | 14726 / 14763 | 6120 | 2301 | -687.19 | 312.81 | 68.7 |
| 5 | gemini-3.1-pro | 99.6 | 14709 / 14762 | 6135 | 2341 | -453.25 | 546.75 | 52.9 |
| 6 | qwen-3.8-max | 99.1 | 14627 / 14756 | 6771 | 2474 | -759.04 | 240.96 | 75.9 |
| 7 | grok-4.6 | 97.1 | 14332 / 14755 | 5142 | 1826 | -765.02 | 234.98 | 77.3 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-09-30, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-09-30}
}