GTO Wizard Benchmark: leaderboard
Metric: AIVAT luck-adjusted win rate in big blinds per hundred hands against GTO Wizard AI over 5,000 heads-up no-limit hands (open scale, 0 is break-even against the bot); zero-shot text prompts, no tools; higher is better. Source: arxiv.org. Saturation forecast: Around May 2027. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 (xHigh) | -17.84 | #76 (GPT-5.4) |
| 2 | Claude Opus 4.6 | -20.35 | #60 |
| 3 | Claude Opus 4.5 | -22.26 | #79 |
| 4 | Gemini 3 Pro | -30.06 | #77 |
| 5 | Gemini 3.1 Pro (Preview) | -30.83 | #54 |
| 6 | Gemini 2.5 Pro | -39.19 | #145 |
| 7 | Kimi K2.5 | -41.43 | #139 |
| 8 | GPT-5.4 (Non-reasoning) | -57.5 | #76 (GPT-5.4) |
| 9 | GPT-4o | -60.9 | #333 |
| 10 | GPT-5.4 Mini (Non-reasoning) | -107.87 | #202 (GPT-5.4 Mini) |
| 11 | GPT-4 | -136.17 | #423 |
| 12 | GPT-5.4 Nano | -189.73 | #320 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=gto-wizard-benchmark · How It Works · Data refreshed daily, snapshot 2026-10-11.