Skip to content

Benchmark

Arena ELO - Industry Medicine and Healthcare

People compare model answers and choose which they prefer. Higher scores are better.

Models measured
336
Scores recorded
391
Sources
1
IQ weight
1.38

Score distribution

1,319.8
Mean
1,368.4
Median
152.6
Std dev
1,071.7
10th percentile
1,469.7
90th percentile
819.1
Min
819.11,538.2
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.38 for chat models, measured over 336 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
351Gemma 1.1 7B IT· LMArena data1,072.4
352Llama 2 13B Chat· LMArena data1,071.7
353Mistral 7B Instruct v0.2· LMArena data1,068
354DBRX Instruct Preview· LMArena data1,067.9
355OpenChat 3.5· LMArena data1,065.9
356WizardLM 13B· LMArena data1,064.9
357Snowflake Arctic Instruct· LMArena data1,063.3
358DeepSeek LLM 67B Chat· LMArena data1,061.7
359Vicuna 33B· LMArena data1,060.3
360Tulu 2 DPO 70B· LMArena data1,059.9
361Granite 3.0 8B Instruct· LMArena data1,058.1
362Nous Hermes 2 Mixtral 8x7B DPO· LMArena data1,056.3
363Qwen1.5-7B-Chat· LMArena data1,056.1
364OpenHermes 2.5 Mistral 7B· LMArena data1,051.9
365SOLAR 10.7B Instruct v1.0· LMArena data1,047.3
366Phi-3 Mini 4K InstructJune 2024· LMArena data1,042.3
367Llama 2 7B Chat· LMArena data1,036.1
368OLMo 7B Instruct· LMArena data1,034.8
369Phi-3 Mini 4K Instruct· LMArena data1,030.1
370Gemma 7B IT· LMArena data1,027.9
371Zephyr 7B Beta· LMArena data1,027.1
372Code Llama 34B Instruct· LMArena data1,025.9
373Vicuna 13B· LMArena data1,019.2
374Llama 3.2 1B Instruct· LMArena data1,009.2
375Qwen-14B-Chat· LMArena data1,009.1
376GPT-3.5 Turbo1106· LMArena data1,006
377Granite 3.0 2B Instruct· LMArena data1,003.4
378Vicuna 7B· LMArena data997.9
379Phi-3 Mini 128K Instruct· LMArena data995.9
380Mistral 7B Instruct· LMArena data993.7
381Gemma 1.1 2B IT· LMArena data990.4
382StripedHyena Nous 7B· LMArena data984.7
383PaLM 2· LMArena data961.7
384Koala 13B· LMArena data956.1
385Qwen1.5-4B-Chat· LMArena data955.5
386RWKV-4 Raven 14B· LMArena data944.5
387Gemma 2B IT· LMArena data938.3
388ChatGLM3 6B· LMArena data892.4
389ChatGLM 6B· LMArena data824.1
390Alpaca 13B· LMArena data820.1
391OpenAssistant Pythia 12B· LMArena data819.1

Showing 351–391 of 391 results.

Data credits: LMArena, CC BY 4.0 (licence)