| # | Model | Arena score | Samples |
|---|---|---|---|
| 341 | 1,183±9 | 6,638 | |
| 342 | openchat-3.5Not listed | 1,183±10 | 7,968 |
| 343 | openchat-3.5-0106Not listed | 1,182±8 | 12,637 |
| 344 |  gemma-1.1-7b-itGoogle | 1,182±6 | 23,893 |
| 345 | snowflake-arctic-instructNot listed | 1,180±6 | 32,832 |
| 346 | 1,179±11 | 3,188 | |
| 347 |
| 1,177±10 |
| 6,535 |
| 348 | openhermes-2.5-mistral-7bNot listed | 1,176±10 | 5,006 |
|---|
| 349 | vicuna-33bNot listed | 1,173±6 | 22,479 |
|---|
| 350 | starling-lm-7b-betaNot listed | 1,171±7 | 16,056 |
|---|
| 351 | phi-3-small-8k-instructMicrosoft | 1,171±6 | 17,766 |
|---|
| 352 | llama-2-70b-chatMeta | 1,170±5 | 38,492 |
|---|
| 353 | starling-lm-7b-alphaNot listed | 1,167±8 | 10,224 |
|---|
| 354 | 1,166±8 | 7,936 |
| 355 | nous-hermes-2-mixtral-8x7b-dpoNot listed | 1,164±12 | 3,777 |
|---|
| 356 | 1,156±8 | 6,837 |
| 357 | llama2-70b-steerlm-chatNvidia | 1,154±13 | 3,585 |
|---|
| 358 | qwq-32b-previewAlibaba | 1,154±11 | 3,231 |
|---|
| 359 | solar-10.7b-instruct-v1.0Not listed | 1,152±13 | 4,155 |
|---|
| 360 | dolphin-2.2.1-mistral-7bNot listed | 1,152±15 | 1,679 |
|---|
Dots: score · lines: published uncertainty