Skip to content

Benchmark

Arena ELO - Multi Turn

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

Models measured
364
Scores recorded
421
Sources
1
IQ weight
1.21

Score distribution

1,304.7
Mean
1,350
Median
160.8
Std dev
1,057.9
10th percentile
1,467.2
90th percentile
740.3
Min
740.31,569.6
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.21 for chat models, measured over 364 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
251Hunyuan Turbo0110· LMArena data1,303.4
252GPT 4o2024-05-13· LMArena data1,301.6
253Qwen2.5-Plus1127· LMArena data1,299.2
254Claude 3.5 Sonnet20240620· LMArena data1,299.2
255Granite 4.2 8B· LMArena data1,298.8
256Llama 3.1 405B InstructBF16· LMArena data1,296.8
257DeepSeek V2.51210· LMArena data1,296.6
258Gemini 1.5 Pro002· LMArena data1,296.1
259Step-2 16K Exp202412· LMArena data1,292.3
260Grok 22024-08-13· LMArena data1,290.1
261Olmo 3 32B Think· LMArena data1,289.6
262Granite 4.2 3B· LMArena data1,289.4
263Llama 4 Maverick· LMArena data1,289.3
264GLM 4 Plus· LMArena data1,289
265Ring Flash 2.0· LMArena data1,287.4
266Llama 3.1 405B InstructFP8· LMArena data1,287.2
267Athene V2 Chat· LMArena data1,285.7
268GPT-4o mini2024-07-18· LMArena data1,285
269Hunyuan Large2025-02-10· LMArena data1,284.4
270Mercury· LMArena data1,282.2
271Llama 4 Scout· LMArena data1,280
272Llama 3.3 70B Instruct· LMArena data1,279.5
273GPT 4o2024-08-06· LMArena data1,278.8
274Qwen Max0919· LMArena data1,276.7
275GPT-4.1 nano2025-04-14· LMArena data1,276.6
276Gemma 3n E4B IT· LMArena data1,276.2
277Llama 3.1 Nemotron 70B Instruct· LMArena data1,275.3
278Claude 3 Opus20240229· LMArena data1,275.3
279Hunyuan Standard2025-02-10· LMArena data1,274.8
280Magistral Medium2506· LMArena data1,274.7
281Qwen2.5 72B Instruct· LMArena data1,271.8
282Mistral Small 3.1 24B Instruct2503· LMArena data1,270.1
283Granite 4.1 8B· LMArena data1,269.9
284Gemini Advanced0514· LMArena data1,268.9
285Gemini 1.5 Pro001· LMArena data1,268.1
286GPT OSS 20b· LMArena data1,267.8
287GPT-4 Turbo2024-04-09· LMArena data1,267
288Grok 2 mini2024-08-13· LMArena data1,265.4
289Claude Haiku 3.520241022· LMArena data1,265
290DeepSeek V2.5· LMArena data1,260.6
291Mistral Large2411· LMArena data1,259.6
292Mistral Large 22407· LMArena data1,257.3
293Athene 70B0725· LMArena data1,257.2
294GPT-4 Turbo Preview1106· LMArena data1,256.6
295Llama 3.1 70B Instruct· LMArena data1,256.1
296Gemma 3 4B IT· LMArena data1,255.2
297Hunyuan Large Vision· LMArena data1,253.3
298Gemini 1.5 Flash002· LMArena data1,252.6
299Olmo 3.1 32B Think· LMArena data1,251.8
300Llama 3.1 Tulu 3 70B· LMArena data1,251.6

Showing 251–300 of 421 results.

Data credits: LMArena, CC BY 4.0 (licence)