Skip to content

Benchmark

Arena ELO

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

Models measured
366
Scores recorded
423
Sources
1
IQ weight
1.19

Score distribution

1,312
Mean
1,354.8
Median
146.6
Std dev
1,084.5
10th percentile
1,462.5
90th percentile
833.5
Min
833.51,539.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.19 for chat models, measured over 366 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
351Gemini ProDev API· LMArena data1,148.9
352Zephyr ORPO 141B A35B v0.1· LMArena data1,143.7
353Phi-3 Medium 4K Instruct· LMArena data1,137.6
354Qwen1.5-32B-Chat· LMArena data1,137.2
355Starling LM 7B Beta· LMArena data1,132.1
356Mixtral 8x7B Instruct v0.1· LMArena data1,131.6
357Gemini Pro· LMArena data1,130.6
358Yi 34B Chat· LMArena data1,128.5
359Qwen1.5-14B-Chat· LMArena data1,127.7
360Granite 3.1 2B Instruct· LMArena data1,127.4
361GPT-3.5 Turbo0125· LMArena data1,125
362Tulu 2 DPO 70B· LMArena data1,121.1
363WizardLM 70B· LMArena data1,119.6
364DBRX Instruct Preview· LMArena data1,118.9
365Llama 2 70B Chat· LMArena data1,115.3
366Nous Hermes 2 Mixtral 8x7B DPO· LMArena data1,112.1
367Phi-3 Small 8K Instruct· LMArena data1,109.9
368Llama 3.2 3B· LMArena data1,109.6
369Starling LM 7B Alpha· LMArena data1,107.7
370OpenChat 3.50106· LMArena data1,106.6
371Vicuna 33B· LMArena data1,105.3
372DeepSeek LLM 67B Chat· LMArena data1,105.1
373Snowflake Arctic Instruct· LMArena data1,101
374Llama 2 70B SteerLM Chat· LMArena data1,098.1
375OpenChat 3.5· LMArena data1,097.1
376Granite 3.0 8B Instruct· LMArena data1,096.5
377GPT-3.5 Turbo1106· LMArena data1,094.2
378Gemma 1.1 7B IT· LMArena data1,094
379OpenHermes 2.5 Mistral 7B· LMArena data1,092.5
380Mistral 7B Instruct v0.2· LMArena data1,089.6
381Llama 2 13B Chat· LMArena data1,084.5
382Qwen1.5-7B-Chat· LMArena data1,083.5
383SOLAR 10.7B Instruct v1.0· LMArena data1,083.1
384Dolphin 2.2.1 Mistral 7B· LMArena data1,081
385Phi-3 Mini 4K InstructJune 2024· LMArena data1,080
386Granite 3.0 2B Instruct· LMArena data1,079.9
387WizardLM 13B· LMArena data1,076.6
388Phi-3 Mini 4K Instruct· LMArena data1,073.3
389Zephyr 7B Beta· LMArena data1,069.5
390MPT 30B Chat· LMArena data1,068.6
391Code Llama 34B Instruct· LMArena data1,065.5
392Zephyr 7B Alpha· LMArena data1,058.4
393Vicuna 13B· LMArena data1,057.7
394Code Llama 70B Instruct· LMArena data1,057.3
395Gemma 7B IT· LMArena data1,056.2
396Llama 3.2 1B Instruct· LMArena data1,054.7
397Falcon 180B Chat· LMArena data1,054.4
398Llama 2 7B Chat· LMArena data1,053.4
399Guanaco 33B· LMArena data1,053.4
400Qwen-14B-Chat· LMArena data1,051.1

Showing 351–400 of 423 results.

Data credits: LMArena, CC BY 4.0 (licence)