Benchmarks snapshot — 2026-07-16
frozenImmutable capture of both official leaderboards and the run configuration, written once for this date and never rewritten. Generated at 2026-07-29T12:51:31.625438+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 | 100.0 | 105 / 105 | 51 | 9 | -22.02 | 806.62 | 2.0 |
| 2 | claude-opus-4.8 | 100.0 | 105 / 105 | 65 | 15 | -22.22 | 782.17 | 2.2 |
| 3 | claude-fable-5 | 100.0 | 105 / 105 | 40 | 6 | -20.96 | 823.16 | 1.8 |
| 4 | deepseek-v4-pro | 100.0 | 105 / 105 | 38 | 7 | -11.18 | 873.95 | 1.1 |
| 5 | gemini-3.1-pro | 74.3 | 78 / 105 | 43 | 8 | -20.61 | 847.54 | 1.0 |
| 6 | qwen-3.7-max | 100.0 | 105 / 105 | 69 | 17 | -20.18 | 774.88 | 1.9 |
| 7 | grok-4.5 | 100.0 | 105 / 105 | 50 | 7 | -15.09 | 807.20 | 1.7 |
Official leaderboard — position
| # | Model | OK rate % | OK / total | Closed | Wins | PnL net $ | Equity $ | Max DD % |
|---|
| 1 | gpt-5.6-sol | 100.0 | 105 / 105 | 42 | 11 | -15.95 | 856.27 | 1.6 |
| 2 | claude-opus-4.8 | 100.0 | 105 / 105 | 52 | 13 | -18.42 | 850.06 | 1.8 |
| 3 | claude-fable-5 | 100.0 | 105 / 105 | 38 | 10 | -16.10 | 857.56 | 1.6 |
| 4 | deepseek-v4-pro | 100.0 | 105 / 105 | 33 | 9 | -8.98 | 898.02 | 0.9 |
| 5 | gemini-3.1-pro | 74.3 | 78 / 105 | 33 | 10 | -6.90 | 883.23 | 0.7 |
| 6 | qwen-3.7-max | 100.0 | 105 / 105 | 55 | 19 | -13.72 | 821.38 | 1.4 |
| 7 | grok-4.5 | 100.0 | 105 / 105 | 42 | 13 | -13.95 | 846.05 | 1.4 |
Cite this snapshot
@misc{marketmania_llmbench_s1_2026,
title = {LLM Market Benchmarks, Season 1},
author = {MarketMania},
year = {2026},
note = {Snapshot 2026-07-16, Binance USDT-M futures paper-trading},
url = {https://marketmania.ai/benchmarks/snapshots/2026-07-16}
}