| # | Model | Arena score | Samples |
|---|---|---|---|
| 321 | 1,223±4 | 104,642 | |
| 322 |  gemini-proGoogle | 1,223±12 | 6,390 |
| 323 | c4ai-aya-expanse-8bCohere | 1,223±7 | 9,818 |
| 324 | mistral-mediumMistral | 1,222±5 | 34,550 |
| 325 | 1,220±11 | 2,896 | |
| 326 | zephyr-orpo-141b-A35b-v0.1Not listed | 1,213±11 | 4,652 |
| 327 |
| 1,213±5 |
| 24,146 |
| 328 | 1,211±4 | 49,605 |
| 329 | 1,208±11 | 3,090 |
| 330 |  gpt-3.5-turbo-1106OpenAI | 1,204±9 | 16,619 |
|---|
| 331 | qwen1.5-32b-chatAlibaba | 1,204±6 | 21,741 |
|---|
| 332 | gemma-2-2b-itGoogle | 1,200±4 | 46,616 |
|---|
| 333 | phi-3-medium-4k-instructMicrosoft | 1,198±5 | 25,055 |
|---|
| 334 | mixtral-8x7b-instruct-v0.1Mistral | 1,197±4 | 73,503 |
|---|
| 335 | dbrx-instruct-previewNot listed | 1,195±6 | 32,191 |
|---|
| 336 | qwen1.5-14b-chatAlibaba | 1,191±7 | 17,839 |
|---|
| 337 | internlm2_5-20b-chatNot listed | 1,191±7 | 9,901 |
|---|
| 338 |  deepseek-llm-67b-chatDeepSeek | 1,184±11 | 4,932 |
|---|
| 339 | wizardlm-70bMicrosoft | 1,184±9 | 8,214 |
|---|
| 340 | yi-34b-chatNot listed | 1,183±7 | 15,483 |
|---|
Dots: score · lines: published uncertainty