Benchmarks · reasoning
ChessBench
LLMs play rated chess games against each other, one rating per model and reasoning effort; the value is a Glicko-2 rating within this benchmark's pool, qualified setups only.
18 models · 32 results · updated 2026-10-26 · chessbench.org ↗
Leaderboard
Gemini 4 Argon medium
More from this benchmark
7 published measuresScore vs any published measure7 measures: sub-scores, splits, counts
Breakdown
darker is better within each column · click a column to sort| Model | |||
|---|---|---|---|
| Gemini 4 Argon medium | 65 | 1 | 4 |
| Opus 5.5 xhigh, fallback | 80 | 4 | 6 |
| Sonnet 5.5 xhigh, fallback | 65 | 0 | 9 |
| GPT-6 Astra xhigh | 104 | 1 | 17 |
| Fable 5.1 xhigh, fallback | 85 | 7 | 28 |
| GPT-6.1 Sol xhigh | 48 | 3 | 19 |
| Haiku 5.5 xhigh | 44 | 6 | 20 |
| DeepSeek V4.1 Flash 1017 max | 32 | 6 | 24 |
| GPT-6.1 Terra xhigh | 30 | 5 | 27 |
| Grok 4.7 xhigh | 40 | 23 | 37 |
| Muse Spark 1.3 medium | 42 | 31 | 46 |
| GLM 5.3 high | 45 | 17 | 58 |
| GPT-6 Luna xhigh | 18 | 24 | 40 |
| MiniMax M3.1 xhigh | 15 | 6 | 41 |
| MiMo V2.6 Flash high | 20 | 20 | 56 |
| GLM 5.3 Flash high | 24 | 29 | 68 |
| MiniMax M3 max | 15 | 33 | 71 |
| Qwen 3.7 Plus high | 4 | 38 | 71 |
All results
32 rows| # | Model | Effort | ChessBench |
|---|---|---|---|
| 1 | Gemini 4 Argon | medium | 2170 ±175 |
| 2 | Opus 5.5 | xhigh | 2102 ±161 |
| 3 | Sonnet 5.5 | xhigh | 2089 ±157 |
| 4 | Gemini 4 Argon | high | 2088 ±171 |
| 5 | GPT-6 Astra | xhigh | 2022 ±148 |
| 6 | Opus 5.5 | medium | 1997 ±150 |
| 7 | Fable 5.1 | xhigh | 1891 ±140 |
| 8 | GPT-6.1 Sol | xhigh | 1840 ±149 |
| 9 | Haiku 5.5 | xhigh | 1796 ±144 |
| 10 | GPT-6 Astra | medium | 1767 ±138 |
| 11 | DeepSeek V4.1 Flash 1017 | max | 1687 ±142 |
| 12 | Sonnet 5.5 | medium | 1641 ±134 |
| 13 | GPT-6.1 Sol | medium | 1630 ±138 |
| 14 | GPT-6.1 Terra | xhigh | 1621 ±140 |
| 15 | DeepSeek V4.1 Flash 1017 | high | 1612 ±136 |
| 16 | Fable 5.1 | medium | 1602 ±132 |
| 17 | Haiku 5.5 | medium | 1584 ±134 |
| 18 | Grok 4.7 | xhigh | 1549 ±131 |
| 19 | Muse Spark 1.3 | medium | 1506 ±130 |
| 20 | GLM 5.3 | high | 1501 ±130 |
| 21 | GLM 5.3 | max | 1491 ±130 |
| 22 | GPT-6.1 Terra | medium | 1451 ±134 |
| 23 | Muse Spark 1.3 | xhigh | 1426 ±130 |
| 24 | GPT-6 Luna | xhigh | 1421 ±134 |
| 25 | MiniMax M3.1 | xhigh | 1386 ±140 |
| 26 | MiMo V2.6 Flash | high | 1345 ±134 |
| 27 | GLM 5.3 Flash | high | 1327 ±136 |
| 28 | GLM 5.3 Flash | max | 1279 ±136 |
| 29 | MiniMax M3 | max | 1261 ±139 |
| 30 | MiniMax M3.1 | medium | 1189 ±148 |