Benchmarks snapshot — 2026-09-03
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-09-04T00:20:29.627945+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 | 9084 / 9094 | 4648 | 1608 | -153.12 | 846.88 | 53.5 |
| 2 | claude-opus-5 | 99.8 | 9077 / 9094 | 4162 | 1485 | -75.42 | 924.58 | 45.0 |
| 3 | claude-fable-5 | 99.8 | 9074 / 9094 | 4395 | 1551 | 46.97 | 1046.97 | 42.6 |
| 4 | deepseek-v4-pro | 99.8 | 9076 / 9093 | 3931 | 1408 | -137.71 | 862.29 | 51.6 |
| 5 | gemini-3.1-pro | 99.4 | 9040 / 9092 | 4713 | 1692 | -202.98 | 797.02 | 40.1 |
| 6 | qwen-3.8-max | 98.9 | 8988 / 9086 | 5065 | 1738 | -461.67 | 538.33 | 69.7 |
| 7 | grok-4.6 | 95.4 | 8670 / 9085 | 4201 | 1381 | -444.07 | 555.93 | 65.5 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 99.9 | 9084 / 9094 | 3753 | 1369 | -377.51 | 622.49 | 37.9 |
| 2 | claude-opus-5 | 99.8 | 9077 / 9094 | 3258 | 1227 | -203.44 | 796.56 | 30.1 |
| 3 | claude-fable-5 | 99.8 | 9074 / 9094 | 3526 | 1303 | -206.02 | 793.98 | 35.3 |
| 4 | deepseek-v4-pro | 99.8 | 9076 / 9093 | 3400 | 1258 | -349.74 | 650.26 | 35.0 |
| 5 | gemini-3.1-pro | 99.4 | 9040 / 9092 | 3656 | 1381 | -211.79 | 788.21 | 31.7 |
| 6 | qwen-3.8-max | 98.9 | 8988 / 9086 | 4190 | 1524 | -376.52 | 623.48 | 42.4 |
| 7 | grok-4.6 | 95.4 | 8670 / 9085 | 3355 | 1161 | -462.55 | 537.45 | 46.3 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-09-03, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-09-03}
}