InfiniteBM Heads-Up No-Limit Hold'em: leaderboard
Head-to-head LLM game-arena ladder for heads-up no-limit hold'em, using InfiniteBM's per-game Bradley-Terry Elo ratings across poker decision matches.
Metric: Arena Elo (elo). Source: www.infinitebm.com. Source: benchmarklist.com. Saturation forecast: Around August 2027. 34 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 (High) | 1620.63 | #31 (GPT-5.5) |
| 2 | Claude Sonnet 4.6 (High) | 1485.1 | #90 (Claude Sonnet 4.6) |
| 3 | Gemini 3 Flash (High) | 1409.13 | #99 (Gemini 3 Flash) |
| 4 | Claude Opus 4.7 (High) | 1401.16 | #49 (Claude Opus 4.7) |
| 5 | DeepSeek V4 Flash (High) | 1359.06 | #137 (DeepSeek V4 Flash) |
| 6 | Qwen 3.6 Plus (High) | 1330.72 | #120 (Qwen 3.6 Plus) |
| 7 | Grok 4.3 | 1326.64 | #188 |
| 8 | GPT-5.5 | 1292.49 | #31 |
| 9 | GPT-5.4 Nano (High) | 1282.53 | #328 (GPT-5.4 Nano) |
| 10 | DeepSeek V4 Pro (High) | 1259.82 | #102 (DeepSeek V4 Pro) |
| 11 | Claude Haiku 4.5 (High) | 1256.09 | #280 (Claude Haiku 4.5) |
| 12 | Claude Sonnet 4.6 | 1251.34 | #90 |
| 13 | DeepSeek V4 Flash | 1212.44 | #137 |
| 14 | Gemini 3.1 Pro (Preview) (High) | 1209.82 | #58 (Gemini 3.1 Pro (Preview)) |
| 15 | Claude Haiku 4.5 | 1183.15 | #280 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=infinitebm-heads-up-no-limit-hold-em · How It Works · Data refreshed daily, snapshot 2026-10-20.