Skip to content

Benchmark

Arena ELO Text Factuality - Industry Life and Physical and Social Science

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

Models measured
138
Scores recorded
156
Sources
1
IQ weight
2.35

Score distribution

1,466.8
Mean
1,468.6
Median
33.7
Std dev
1,433.2
10th percentile
1,506.4
90th percentile
1,348.5
Min
1,348.51,551.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.35 for chat models, measured over 138 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101MiniMax M3· LMArena data1,458.1
102Gemini 2.5 Flash· LMArena data1,457.9
103GPT-5.5 Instant· LMArena data1,457.6
104Claude Opus 4.1Thinking 16K, 20250805· LMArena data1,455.7
105Mistral Medium 3.12508· LMArena data1,455.5
106Qwen3.5 27B· LMArena data1,455.2
107DeepSeek-V4-Flash PreviewHigh· LMArena data1,453.9
108Grok 4.7xHigh· LMArena data1,453.5
109Qwen3.6 Plus· LMArena data1,453.3
110MiMo V2 Omni· LMArena data1,452.9
111Beam 1.0 501B A23B· LMArena data1,452.1
112DeepSeek V3.2Thinking· LMArena data1,451.9
113Gemini 3.1 Flash Lite· LMArena data1,450.7
114Mistral Medium 3.5· LMArena data1,450.5
115GPT-5 Chat· LMArena data1,450.5
116DeepSeek V3.2 Exp· LMArena data1,448.5
117Grok 4.1· LMArena data1,448
118Grok 40709· LMArena data1,446.9
119MiMo V2 FlashNon-Thinking· LMArena data1,446.6
120Claude Opus 4.120250805· LMArena data1,446.6
121Claude Haiku 5.5High· LMArena data1,446.4
122Inkling Small· LMArena data1,446.1
123Qwen3.5 122B-A10B· LMArena data1,445
124LongCat-Flash-Chat Exp2602· LMArena data1,443.5
125MiniMax M2.7· LMArena data1,441.8
126Grok 4.3· LMArena data1,440.9
127GPT-6 SolMax· LMArena data1,440.5
128Grok 4 FastReasoning· LMArena data1,440
129Step 3.5 Flash· LMArena data1,439.1
130Grok 4.1Thinking· LMArena data1,438.6
131Solar Pro 4· LMArena data1,438.1
132MiniMax-M2.1 Preview· LMArena data1,438
133Mistral Large 4· LMArena data1,437.1
134Qwen3.5 Flash· LMArena data1,436.9
135Claude Haiku 4.520251001· LMArena data1,436.9
136Qwen3.5 35B A3B· LMArena data1,436
137Kimi K2 Thinking· LMArena data1,435.6
138nova-experimental-chat10-20· LMArena data1,434.1
139Doubao Seed 2.0 Pro· LMArena data1,433.9
140Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,433.2
141GPT 5.4 NanoHigh· LMArena data1,429.5
142OpenAI o32025-04-16· LMArena data1,428
143Grok 4.1 FastReasoning· LMArena data1,426.6
144GPT-5.3 Chat· LMArena data1,425.3
145MiMo V2 FlashThinking· LMArena data1,424.4
146GPT-5 miniHigh· LMArena data1,421
147Nova 2 Lite· LMArena data1,406.3
148MiniMax M2.5· LMArena data1,398.6
149Qwen3 Next 80B A3B Instruct· LMArena data1,398.2
150GLM 4.7 Flash· LMArena data1,396.6

Showing 101–150 of 156 results.

Data credits: LMArena, CC BY 4.0 (licence)