Skip to content

Benchmark

Arena ELO Vision - Chinese

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

Models measured
118
Scores recorded
135
Sources
1
IQ weight
2.18

Score distribution

1,237.1
Mean
1,277.2
Median
130.5
Std dev
1,009
10th percentile
1,368
90th percentile
889.6
Min
889.61,400.6
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.18 for chat models, measured over 118 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101GPT-5 nanoHigh· LMArena data1,175.4
102Claude Sonnet 3.720250219· LMArena data1,172.8
103Gemma 3 27B IT· LMArena data1,163.1
104Mistral Small 3.22506· LMArena data1,162.6
105Mistral Medium 32505· LMArena data1,161.1
106Mistral Small 3.1 24B Instruct2503· LMArena data1,154.2
107Gemini 2.0 Flash001· LMArena data1,144.8
108Llama 4 Maverick· LMArena data1,140.4
109Gemini 1.5 Flash002· LMArena data1,136.6
110GPT 4o2024-05-13· LMArena data1,131.8
111Claude 3.5 Sonnet20241022· LMArena data1,118.2
112Qwen2.5 VL 72B Instruct· LMArena data1,106.7
113Llama 4 Scout· LMArena data1,105.8
114Claude 3.5 Sonnet20240620· LMArena data1,104.9
115Pixtral Large2411· LMArena data1,082.4
116Qwen2-VL-72B· LMArena data1,071.3
117InternVL2 26B· LMArena data1,064.6
118GPT-4 Turbo2024-04-09· LMArena data1,044.7
119GPT-4o mini2024-07-18· LMArena data1,032.9
120Gemini 1.5 Pro001· LMArena data1,030.1
121Gemini 2.0 Flash-Lite Preview02-05· LMArena data1,026
122GPT 4o2024-08-06· LMArena data1,009
123Qwen2 VL 7b Instruct· LMArena data998.9
124Claude 3 Opus20240229· LMArena data993.8
125Gemini 1.5 Flash-8B001· LMArena data973.2
126Gemini 1.5 Flash001· LMArena data959.5
127Llama 3.2 90B Vision Instruct· LMArena data951.9
128Pixtral 12B2409· LMArena data950.2
129InternVL2 4B· LMArena data950
130Claude 3 Sonnet20240229· LMArena data942.1
131Molmo 72B0924· LMArena data935.9
132Claude 3 Haiku20240307· LMArena data915.3
133LLaVA 1.6 34B· LMArena data914.5
134Llama 3.2 11B Vision Instruct· LMArena data914.4
135Molmo 7B-D0924· LMArena data889.6

Showing 101–135 of 135 results.

Data credits: LMArena, CC BY 4.0 (licence)