| # | Model | Arena score | Samples |
|---|---|---|---|
| 121 |  deepseek-v3.1-terminus-thinkingDeepSeek | 1,417±10 | 3,369 |
| 122 | deepseek-v3.1DeepSeek | 1,417±6 | 14,604 |
| 123 | qwen3.5-122b-a10bAlibaba | 1,417±4 | 28,349 |
| 124 | deepseek-v3.1-thinkingDeepSeek | 1,416±7 | 11,462 |
| 125 | deepseek-v3.1-terminusDeepSeek | 1,415±10 | 3,611 |
| 126 |  minimax-m2.7MiniMax | 1,415±4 | 68,700 |
| 127 |
| 1,415±10 |
| 3,347 |
| 128 |  gpt-4.1-2025-04-14OpenAI | 1,414±4 | 49,934 |
|---|
| 129 |  claude-haiku-4-5-20251001Anthropic | 1,414±3 | 128,838 |
|---|
| 130 | qwen3-vl-235b-a22b-instructAlibaba | 1,414±7 | 11,219 |
|---|
| 131 | claude-opus-4-20250514Anthropic | 1,414±4 | 42,837 |
|---|
| 132 | mistral-large-3Mistral | 1,413±3 | 68,591 |
|---|
| 133 | hunyuan-hy3-previewTencent | 1,413±8 | 6,606 |
|---|
| 134 | grok-3-preview-02-24SpaceXAI | 1,412±4 | 32,409 |
|---|
| 135 |  glm-4.5Z.ai | 1,411±5 | 23,707 |
|---|
| 136 | grok-4-0709SpaceXAI | 1,411±4 | 39,299 |
|---|
| 137 |  gemini-2.5-flashGoogle | 1,410±2 | 122,716 |
|---|
| 138 | mistral-medium-2508Mistral | 1,409±3 | 92,692 |
|---|
| 139 | qwen3.5-27bAlibaba | 1,408±4 | 27,228 |
|---|
| 140 | grok-4-fast-reasoningSpaceXAI | 1,405±5 | 17,971 |
|---|
Dots: score · lines: published uncertainty