Benchmarks snapshot — 2026-09-19
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-09-20T00:20:35.568030+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 | 12441 / 12454 | 6525 | 2299 | -345.96 | 654.04 | 104.7 |
| 2 | claude-opus-5 | 99.8 | 12435 / 12454 | 5732 | 2064 | -267.46 | 732.54 | 92.9 |
| 3 | claude-fable-5 | 99.8 | 12434 / 12454 | 6201 | 2243 | 65.32 | 1065.32 | 90.8 |
| 4 | deepseek-v4-pro | 99.9 | 12436 / 12453 | 6023 | 2225 | -312.61 | 687.39 | 92.0 |
| 5 | gemini-3.1-pro | 99.6 | 12399 / 12452 | 6649 | 2434 | -613.11 | 386.89 | 80.2 |
| 6 | qwen-3.8-max | 99.1 | 12337 / 12446 | 6967 | 2444 | -914.41 | 85.59 | 111.5 |
| 7 | grok-4.6 | 96.7 | 12029 / 12445 | 5572 | 1879 | -713.47 | 286.53 | 109.1 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.9 | 12441 / 12454 | 5137 | 1846 | -710.25 | 289.75 | 75.4 |
| 2 | claude-opus-5 | 99.8 | 12435 / 12454 | 4388 | 1624 | -484.20 | 515.80 | 51.7 |
| 3 | claude-fable-5 | 99.8 | 12434 / 12454 | 4844 | 1769 | -481.24 | 518.76 | 55.8 |
| 4 | deepseek-v4-pro | 99.9 | 12436 / 12453 | 5013 | 1859 | -602.51 | 397.49 | 67.3 |
| 5 | gemini-3.1-pro | 99.6 | 12399 / 12452 | 5108 | 1918 | -477.50 | 522.50 | 52.9 |
| 6 | qwen-3.8-max | 99.1 | 12337 / 12446 | 5711 | 2072 | -705.79 | 294.21 | 75.6 |
| 7 | grok-4.6 | 96.7 | 12029 / 12445 | 4410 | 1524 | -757.92 | 242.08 | 76.0 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-09-19, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-09-19}
}