| # | Model | Arena score | Samples |
|---|---|---|---|
| 81 |  claude-opus-4-1-20250805Anthropic | 1,389±11 | 6,769 |
| 82 |  minimax-m2.1-previewMiniMax | 1,387±10 | 7,281 |
| 83 |  gpt-5.4OpenAI | 1,387±13 | 2,493 |
| 84 | claude-sonnet-4-5-20250929Anthropic | 1,385±7 | 15,150 |
| 85 | minimax-m2.5MiniMax | 1,384±8 | 7,186 |
| 86 | 1,383±5 | 20,911 | |
| 87 |
grok-4.20-beta-0309-reasoningSpaceXAI |
|---|
| 1,374±6 |
| 14,571 |
| 88 | solar-pro4Upstage | 1,371±17 | 1,403 |
|---|
| 89 | 1,370±12 | 3,491 |
| 90 |  gemma-4-31bGoogle | 1,364±7 | 10,139 |
|---|
| 91 | gemma-4-26b-a4bGoogle | 1,361±17 | 1,442 |
|---|
| 92 |  deepseek-v3.2-thinkingDeepSeek | 1,361±9 | 6,633 |
|---|
| 93 | muse-glimmerMeta | 1,360±16 | 1,512 |
|---|
| 94 | qwen3.5-122b-a10bAlibaba | 1,358±8 | 7,831 |
|---|
| 95 | qwen3.5-27bAlibaba | 1,357±8 | 7,427 |
|---|
| 96 | grok-4.3SpaceXAI | 1,357±6 | 14,192 |
|---|
| 97 | hunyuan-hy3-previewTencent | 1,356±18 | 1,395 |
|---|
| 98 | laguna-m.1Poolside | 1,347±10 | 5,062 |
|---|
| 99 | gpt-5.1OpenAI | 1,341±9 | 10,326 |
|---|
| 100 |  glm-4.6Z.ai | 1,341±11 | 6,600 |
|---|
Dots: score · lines: published uncertainty