Skip to content

Benchmark

Arena ELO - Non English

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

Models measured
366
Scores recorded
423
Sources
1
IQ weight
1.20

Score distribution

1,288.7
Mean
1,334.4
Median
160.8
Std dev
1,032.5
10th percentile
1,449.6
90th percentile
781.3
Min
781.31,534.5
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.20 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
101MiMo V2 Pro· LMArena data1,416.8
102GPT-6.1 TerraMax· LMArena data1,416
103Mistral Large 3· LMArena data1,414.2
104GPT-4.5 Preview2025-02-27· LMArena data1,412.9
105GPT 5.1· LMArena data1,412.9
106MiniMax M3· LMArena data1,412.1
107DeepSeek R10528· LMArena data1,411.7
108Beam 1.0 501B A23B· LMArena data1,411.2
109Gemini 3.1 Flash Lite· LMArena data1,411.2
110Grok 3 Preview02-24· LMArena data1,410.5
111DeepSeek-V4-Flash PreviewHigh· LMArena data1,410
112Qwen3 235B A22B Instruct 25072507· LMArena data1,409.4
113Gemini 2.5 Flash· LMArena data1,409.3
114DeepSeek V3.2· LMArena data1,409
115Mistral Medium 3.12508· LMArena data1,408.1
116DeepSeek V3.1 Terminus· LMArena data1,408
117Qwen3 Next 80B A3B Instruct· LMArena data1,406.9
118Kimi K2.5Instant· LMArena data1,406.4
119DeepSeek V3.1 TerminusThinking· LMArena data1,405.5
120GPT 5.2· LMArena data1,405.2
121Claude Opus 4.120250805· LMArena data1,405.2
122Mistral Medium 3.5· LMArena data1,405.1
123GPT 5.2High· LMArena data1,405
124GPT-5.4 miniHigh· LMArena data1,404.9
125GPT-6.2 SolMax· LMArena data1,404.7
126Qwen3 VL 235B· LMArena data1,404.7
127DeepSeek V3.2 ExpThinking· LMArena data1,404.4
128DeepSeek V3.2 Exp· LMArena data1,404.4
129nova-experimental-chat11-10· LMArena data1,404.3
130MiMo V2.5· LMArena data1,404.2
131GPT-6.2 AstraMax· LMArena data1,404.1
132Claude Opus 4.1Thinking 16K, 20250805· LMArena data1,403.7
133LongCat Flash Chat· LMArena data1,403.6
134MiMo V2 Omni· LMArena data1,403
135Grok 40709· LMArena data1,402.5
136Inkling Small· LMArena data1,402.3
137OpenAI o32025-04-16· LMArena data1,401.2
138Qwen3.5 122B-A10B· LMArena data1,400.3
139Mistral Large 4· LMArena data1,400.2
140DeepSeek V3.1Thinking· LMArena data1,400
141DeepSeek V3.1· LMArena data1,399.9
142Qwen3 Max2025-09-23· LMArena data1,399.8
143DeepSeek V3.2Thinking· LMArena data1,399.2
144LongCat-Flash-Chat Exp2602· LMArena data1,399.1
145nova-experimental-chat12-10· LMArena data1,398.3
146Kimi K2 Thinking· LMArena data1,397.5
147Qwen 3 235B A22B2507, thinking· LMArena data1,397.4
148GPT 5High· LMArena data1,397.3
149Gemini 2.5 Flash Preview09-2025· LMArena data1,395.9
150Grok 4 FastNon-Reasoning· LMArena data1,395.4

Showing 101–150 of 423 results.

Data credits: LMArena, CC BY 4.0 (licence)