Skip to content

Benchmark

Arena ELO - Industry Life and Physical and Social Science

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

Models measured
364
Scores recorded
421
Sources
1
IQ weight
1.24

Score distribution

1,316.4
Mean
1,364.4
Median
158.9
Std dev
1,071.5
10th percentile
1,475.1
90th percentile
800.9
Min
800.91,549.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.24 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
101DeepSeek V3.2 ExpThinking· LMArena data1,443.2
102Grok 4.1· LMArena data1,442.3
103ChatGPT-4o Latest20250326· LMArena data1,442.1
104Grok 4.20 Beta 1· LMArena data1,441.7
105Claude Sonnet 4.5High, 32K, 20250929· LMArena data1,440.6
106Qwen3.6 Plus· LMArena data1,439.6
107MiMo V2.5· LMArena data1,439.5
108GPT 5.1· LMArena data1,439.3
109GPT-5.2 Chat20260210· LMArena data1,438.2
110MiMo V2 Omni· LMArena data1,437.7
111Grok 3 Preview02-24· LMArena data1,437.4
112Grok 4.6High· LMArena data1,437.3
113Qwen3 235B A22B Instruct 25072507· LMArena data1,437.1
114Grok 4.1Thinking· LMArena data1,437
115DeepSeek-V4-Flash PreviewHigh· LMArena data1,436.8
116Qwen3.5 27B· LMArena data1,436
117Grok 40709· LMArena data1,434.9
118Qwen3 Next 80B A3B Instruct· LMArena data1,434.3
119Hunyuan T120250711· LMArena data1,434.1
120Gemini 2.5 Flash Preview09-2025· LMArena data1,434.1
121GPT-5.6 LunaxHigh· LMArena data1,434.1
122Mistral Large 4· LMArena data1,433.8
123Qwen 3 235B A22B2507, thinking· LMArena data1,433.5
124DeepSeek V3.1· LMArena data1,433.3
125Kimi K2.5Instant· LMArena data1,433.2
126Gemini 2.5 Flash· LMArena data1,432.6
127GPT-6.2 SolMax· LMArena data1,432.4
128LongCat-Flash-Chat Exp2602· LMArena data1,432.2
129Qwen3.5 122B-A10B· LMArena data1,432
130DeepSeek R10528· LMArena data1,430.2
131DeepSeek V3.2 Exp· LMArena data1,429.6
132OpenAI o32025-04-16· LMArena data1,429.4
133Inkling Small· LMArena data1,429.2
134Beam 1.0 501B A23B· LMArena data1,429.1
135GPT-5.5 Instant· LMArena data1,428.4
136NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,428.2
137DeepSeek V3.1Thinking· LMArena data1,427.8
138Mistral Medium 3.5· LMArena data1,427.4
139Grok 4 FastReasoning· LMArena data1,426.9
140DeepSeek V3.2Thinking· LMArena data1,426.2
141Gemini 3.1 Flash Lite· LMArena data1,426
142GPT 5.2High· LMArena data1,425
143LongCat Flash Chat· LMArena data1,424.1
144nova-experimental-chat10-20· LMArena data1,423.6
145GPT-6.1 TerraMax· LMArena data1,422.3
146MiMo V2 FlashNon-Thinking· LMArena data1,422.2
147Claude Opus 4.1Thinking 16K, 20250805· LMArena data1,421.9
148GPT 5.2· LMArena data1,421.2
149Grok 4.1 FastReasoning· LMArena data1,420.5
150GPT-4.5 Preview2025-02-27· LMArena data1,420.3

Showing 101–150 of 421 results.

Data credits: LMArena, CC BY 4.0 (licence)