Skip to content

Benchmark

Arena ELO Vision Style-Controlled

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

Models measured
147
Scores recorded
168
Sources
1
IQ weight
1.56

Score distribution

1,187.6
Mean
1,215.3
Median
96.7
Std dev
1,025.4
10th percentile
1,287.8
90th percentile
881.3
Min
881.31,308.8
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.56 for chat models, measured over 147 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51GPT-5.6 LunaxHigh· LMArena data1,255.7
52Grok 4.20Reasoning, 0309, beta· LMArena data1,255.4
53Kimi K2.5Thinking· LMArena data1,252.6
54GPT 5.1High· LMArena data1,250.9
55Grok 4.20 Multi-Agent0309, beta· LMArena data1,250.7
56Grok 4.7xHigh· LMArena data1,250
57GPT-5.4 miniHigh· LMArena data1,249.8
58MiMo V2.6 Pro· LMArena data1,247.5
59Gemini 2.5 Pro· LMArena data1,247.5
60Step 5 Preview· LMArena data1,246.5
61MiMo V2.6 Flash· LMArena data1,245.8
62Qwen3.5 397B A17B· LMArena data1,245.4
63Qwen 3.8 27B· LMArena data1,244.4
64GPT 5.2High· LMArena data1,242.7
65Gemma 4 26B A4B· LMArena data1,241.2
66Grok 4.3· LMArena data1,241.1
67GPT 5.1· LMArena data1,240.3
68ChatGPT-4o Latest20250326· LMArena data1,238.1
69Kimi K2.5Instant· LMArena data1,235.5
70Gemini 3.1 Flash Lite· LMArena data1,234.4
71GPT-6 LunaMax· LMArena data1,234.1
72MiMo V2.5· LMArena data1,233.8
73Mistral Large 4· LMArena data1,233.2
74MiniMax M3· LMArena data1,230.9
75Gemini 2.5 Flash Preview09-2025· LMArena data1,229.2
76GPT 5.2· LMArena data1,227.7
77Qwen3.5 122B-A10B· LMArena data1,225.6
78GPT-5 Chat· LMArena data1,225.5
79GPT-4.5 Preview2025-02-27· LMArena data1,225.4
80ERNIE-5.0-Preview1220· LMArena data1,218.7
81MiMo V2 Omni· LMArena data1,216.1
82OpenAI o32025-04-16· LMArena data1,216.1
83Gemini 2.5 Flash· LMArena data1,215.5
84Qwen3.5 27B· LMArena data1,215.3
85Qwen3 VL 235B· LMArena data1,214.3
86GPT 4.12025-04-14· LMArena data1,213.9
87GPT 5High· LMArena data1,211.5
88NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,211.1
89Inkling Small· LMArena data1,208.1
90Claude Opus 4Thinking 16K, 20250514· LMArena data1,207.9
91Claude Sonnet 4Thinking 32K, 20250514· LMArena data1,206.8
92o4 Mini2025-04-16· LMArena data1,201.3
93GPT-4.1 mini2025-04-14· LMArena data1,201
94Mistral Large 3· LMArena data1,200.4
95Mistral Medium 3.5· LMArena data1,198.9
96GPT 5.4 NanoHigh· LMArena data1,198.6
97Grok 4.1 FastReasoning· LMArena data1,196.6
98Claude Sonnet 3.7Thinking 32K, 20250219· LMArena data1,193.1
99o12024-12-17· LMArena data1,193
100Claude Opus 420250514· LMArena data1,189.2

Showing 51–100 of 168 results.

Data credits: LMArena, CC BY 4.0 (licence)