| # | Model | Arena score | Samples |
|---|---|---|---|
| 201 |  gpt-oss-120bOpenAI | 1,352±4 | 29,948 |
| 202 |  gemini-1.5-pro-002Google | 1,351±3 | 55,606 |
| 203 | 1,350±6 | 11,363 | |
| 204 | step-3StepFun | 1,349±8 | 6,277 |
| 205 | hunyuan-turbos-20250226Tencent | 1,349±12 | 2,220 |
| 206 | o3-miniOpenAI | 1,348±4 | 56,652 |
| 207 |
| 1,348±12 |
| 2,549 |
| 208 | qwen3-32bAlibaba | 1,347±9 | 3,926 |
|---|
| 209 | 1,347±11 | 2,775 |
| 210 | mercury-2Inception AI | 1,346±11 | 3,042 |
|---|
| 211 | gpt-4o-2024-05-13OpenAI | 1,346±3 | 112,881 |
|---|
| 212 | qwen-plus-0125Alibaba | 1,346±8 | 5,819 |
|---|
| 213 |  minimax-m2MiniMax | 1,346±8 | 6,752 |
|---|
| 214 | ling-flash-2.0Ant Group | 1,344±7 | 6,851 |
|---|
| 215 | 1,343±10 | 3,313 |
| 216 |  claude-3-5-sonnet-20240620Anthropic | 1,343±3 | 82,419 |
|---|
| 217 |  glm-4-plus-0111Z.ai | 1,343±8 | 5,760 |
|---|
| 218 | gemma-3-12b-itGoogle | 1,342±10 | 3,829 |
|---|
| 219 | 1,342±11 | 3,261 |
| 220 | hunyuan-turbo-0110Tencent | 1,341±12 | 2,290 |
|---|
Dots: score · lines: published uncertainty