Benchmarks snapshot — 2026-09-22
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-09-23T00:20:36.581081+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 | 13071 / 13084 | 7030 | 2609 | 563.45 | 1563.45 | 104.7 |
| 2 | claude-opus-5 | 99.9 | 13065 / 13084 | 6166 | 2332 | 393.64 | 1393.64 | 92.9 |
| 3 | claude-fable-5 | 99.8 | 13064 / 13084 | 6708 | 2552 | 952.45 | 1952.45 | 90.8 |
| 4 | deepseek-v4-pro | 99.7 | 13046 / 13083 | 6544 | 2506 | 220.26 | 1220.26 | 92.0 |
| 5 | gemini-3.1-pro | 99.6 | 13029 / 13082 | 7129 | 2693 | -270.15 | 729.85 | 80.2 |
| 6 | qwen-3.8-max | 99.1 | 12963 / 13076 | 7415 | 2669 | -637.83 | 362.17 | 111.5 |
| 7 | grok-4.6 | 96.8 | 12657 / 13075 | 5944 | 2090 | -223.36 | 776.64 | 109.1 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.9 | 13071 / 13084 | 5471 | 2033 | -574.94 | 425.06 | 75.4 |
| 2 | claude-opus-5 | 99.9 | 13065 / 13084 | 4680 | 1779 | -372.19 | 627.81 | 51.7 |
| 3 | claude-fable-5 | 99.8 | 13064 / 13084 | 5175 | 1932 | -408.67 | 591.33 | 55.8 |
| 4 | deepseek-v4-pro | 99.7 | 13046 / 13083 | 5407 | 2050 | -537.26 | 462.74 | 67.3 |
| 5 | gemini-3.1-pro | 99.6 | 13029 / 13082 | 5460 | 2116 | -346.04 | 653.96 | 52.9 |
| 6 | qwen-3.8-max | 99.1 | 12963 / 13076 | 6080 | 2257 | -618.64 | 381.36 | 75.6 |
| 7 | grok-4.6 | 96.8 | 12657 / 13075 | 4681 | 1664 | -689.18 | 310.82 | 77.3 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-09-22, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-09-22}
}