| # | Model | Arena score | Samples |
|---|---|---|---|
| 381 | vicuna-7bNot listed | 1,115±9 | 6,923 |
| 382 | smollm2-1.7b-instructNot listed | 1,114±14 | 2,199 |
| 383 | 1,111±8 | 8,045 | |
| 384 | mistral-7b-instructMistral | 1,110±9 | 8,977 |
| 385 | llama-2-7b-chatMeta | 1,108±7 | 14,148 |
| 386 |  gemma-2b-itGoogle | 1,093±11 | 4,780 |
| 387 |
| 1,091±9 |
| 7,597 |
| 388 | 1,073±11 | 6,328 |
| 389 | koala-13bNot listed | 1,070±10 | 6,965 |
|---|
| 390 | alpaca-13bNot listed | 1,070±11 | 5,745 |
|---|
| 391 | gpt4all-13b-snoozyNot listed | 1,067±15 | 1,743 |
|---|
| 392 | mpt-7b-chatNot listed | 1,063±12 | 3,924 |
|---|
| 393 | chatglm3-6bNot listed | 1,056±12 | 4,658 |
|---|
| 394 | RWKV-4-Raven-14BNot listed | 1,042±11 | 4,845 |
|---|
| 395 | chatglm2-6bNot listed | 1,024±14 | 2,658 |
|---|
| 396 | oasst-pythia-12bNot listed | 1,023±11 | 6,310 |
|---|
| 397 | chatglm-6bNot listed | 995±13 | 4,914 |
|---|
| 398 | fastchat-t5-3bNot listed | 992±12 | 4,203 |
|---|
| 399 | dolly-v2-12bNot listed | 982±13 | 3,412 |
|---|
| 400 | llama-13bMeta | 975±16 | 2,391 |
|---|
Dots: score · lines: published uncertainty