Skip to content

Benchmark

Arena ELO - Industry Business and Management and Financial Operations

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

Models measured
359
Scores recorded
416
Sources
1
IQ weight
1.28

Score distribution

1,295.6
Mean
1,344.1
Median
158.7
Std dev
1,054.4
10th percentile
1,457
90th percentile
734.2
Min
734.21,520.2
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.28 for chat models, measured over 359 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
351Starling LM 7B Beta· LMArena data1,103.8
352Phi-3 Medium 4K Instruct· LMArena data1,098.7
353QwQ 32B Preview· LMArena data1,098.3
354Qwen1.5-32B-Chat· LMArena data1,094.2
355Zephyr ORPO 141B A35B v0.1· LMArena data1,089
356Yi 34B Chat· LMArena data1,088.6
357Mixtral 8x7B Instruct v0.1· LMArena data1,083.6
358Gemini Pro· LMArena data1,083.1
359Qwen1.5-14B-Chat· LMArena data1,082.8
360Llama 2 70B Chat· LMArena data1,082.8
361WizardLM 70B· LMArena data1,078.4
362Llama 2 70B SteerLM Chat· LMArena data1,078.2
363Tulu 2 DPO 70B· LMArena data1,077.3
364Phi-3 Small 8K Instruct· LMArena data1,077.1
365GPT-3.5 Turbo0125· LMArena data1,076.1
366OpenChat 3.50106· LMArena data1,074.1
367Llama 3.2 3B· LMArena data1,073.6
368Starling LM 7B Alpha· LMArena data1,072.6
369DBRX Instruct Preview· LMArena data1,072.1
370Nous Hermes 2 Mixtral 8x7B DPO· LMArena data1,071.2
371Qwen1.5-7B-Chat· LMArena data1,063.6
372Gemma 1.1 7B IT· LMArena data1,062.9
373Llama 2 13B Chat· LMArena data1,055.6
374Vicuna 33B· LMArena data1,054.4
375DeepSeek LLM 67B Chat· LMArena data1,047.6
376Granite 3.0 8B Instruct· LMArena data1,040.5
377Mistral 7B Instruct v0.2· LMArena data1,038.1
378OpenChat 3.5· LMArena data1,036.1
379Granite 3.0 2B Instruct· LMArena data1,035.2
380Code Llama 34B Instruct· LMArena data1,033.6
381Phi-3 Mini 4K Instruct· LMArena data1,032.1
382Snowflake Arctic Instruct· LMArena data1,031.4
383Llama 2 7B Chat· LMArena data1,027.8
384Gemma 7B IT· LMArena data1,025
385OpenHermes 2.5 Mistral 7B· LMArena data1,024.3
386Phi-3 Mini 4K InstructJune 2024· LMArena data1,022.9
387SOLAR 10.7B Instruct v1.0· LMArena data1,019.9
388GPT-3.5 Turbo1106· LMArena data1,019.6
389OLMo 7B Instruct· LMArena data1,019.6
390MPT 30B Chat· LMArena data1,008.4
391WizardLM 13B· LMArena data1,006.3
392Vicuna 13B· LMArena data1,005.9
393Qwen-14B-Chat· LMArena data1,001.5
394Zephyr 7B Beta· LMArena data1,000.4
395Llama 3.2 1B Instruct· LMArena data999.6
396Gemma 2B IT· LMArena data998.8
397Phi-3 Mini 128K Instruct· LMArena data990
398Gemma 1.1 2B IT· LMArena data980.8
399Guanaco 33B· LMArena data972.8
400Vicuna 7B· LMArena data972.6

Showing 351–400 of 416 results.

Data credits: LMArena, CC BY 4.0 (licence)