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
251o3 Mini· LMArena data1,289.5
252Qwen2.5-Plus1127· LMArena data1,288.8
253Granite 4.2 3B· LMArena data1,287.8
254O1 Mini· LMArena data1,287
255Llama 3.3 Nemotron Super 49B v1· LMArena data1,286.4
256Gemini 1.5 Pro002· LMArena data1,285.9
257GPT OSS 20b· LMArena data1,283.3
258Step-2 16K Exp202412· LMArena data1,283
259Athene V2 Chat· LMArena data1,273.7
260GLM 4 Plus· LMArena data1,273.1
261Claude Sonnet 3.720250219· LMArena data1,272.8
262Yi Lightning· LMArena data1,271.1
263Claude Sonnet 3.7Thinking 32K, 20250219· LMArena data1,269.3
264Granite 4.1 8B· LMArena data1,268.5
265GPT-4.1 nano2025-04-14· LMArena data1,266.5
266Grok 22024-08-13· LMArena data1,265.1
267GPT-4o mini2024-07-18· LMArena data1,264.8
268Gemini 1.5 Flash002· LMArena data1,264.5
269Llama 3.1 Nemotron 70B Instruct· LMArena data1,261.7
270GPT 4o2024-05-13· LMArena data1,261.5
271Llama 4 Maverick· LMArena data1,260.7
272DeepSeek V2.51210· LMArena data1,259.2
273Mistral Small 3.1 24B Instruct2503· LMArena data1,257.1
274Llama 4 Scout· LMArena data1,256.5
275Qwen Max0919· LMArena data1,256
276Hunyuan Standard2025-02-10· LMArena data1,254.9
277Claude 3.5 Sonnet20241022· LMArena data1,254.9
278Grok 2 mini2024-08-13· LMArena data1,253.7
279Olmo 3.1 32B Think· LMArena data1,253.6
280Qwen2.5 72B Instruct· LMArena data1,252.8
281Gemini 1.5 Pro001· LMArena data1,248.5
282DeepSeek V2.5· LMArena data1,248.2
283Llama 3.1 405B InstructFP8· LMArena data1,247.5
284Gemini Advanced0514· LMArena data1,246.2
285Athene 70B0725· LMArena data1,245.5
286Llama 3.1 405B InstructBF16· LMArena data1,244.9
287Llama 3.3 70B Instruct· LMArena data1,242.9
288Hunyuan Large2025-02-10· LMArena data1,241.2
289Mistral Large2411· LMArena data1,238
290Llama 3.1 70B Instruct· LMArena data1,235
291Claude 3.5 Sonnet20240620· LMArena data1,234.8
292GPT 4o2024-08-06· LMArena data1,231.7
293Nova Pro 1.0· LMArena data1,229.1
294Hunyuan Large Vision· LMArena data1,227.1
295Llama 3.1 Tulu 3 70B· LMArena data1,226
296Mistral Large 22407· LMArena data1,225.9
297Gemini 1.5 Flash001· LMArena data1,225.4
298Qwen 2.5 Coder 32B Instruct· LMArena data1,223.8
299Magistral Medium2506· LMArena data1,222.9
300Claude Haiku 3.520241022· LMArena data1,222.6

Showing 251–300 of 416 results.

Data credits: LMArena, CC BY 4.0 (licence)