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
51GPT-5.6 SolxHigh· LMArena data1,309.4
52Gemini 3.5 Flash Lite· LMArena data1,309.3
53GPT 5.2High· LMArena data1,305.2
54MiniMax M3· LMArena data1,305
55Grok 4.20Reasoning, 0309, beta· LMArena data1,305
56Qwen3.5 27B· LMArena data1,302.3
57GPT-5.6 LunaxHigh· LMArena data1,300.8
58Gemini 2.5 Pro· LMArena data1,299.6
59Grok 4.20 Multi-Agent0309, beta· LMArena data1,299.3
60Qwen3.5 122B-A10B· LMArena data1,298.2
61Inkling Small· LMArena data1,286.7
62GPT-5.4 miniHigh· LMArena data1,285.8
63MiMo V2 Omni· LMArena data1,285.7
64Grok 4.6High· LMArena data1,285.6
65Gemini 2.5 Flash Preview09-2025· LMArena data1,284
66Gemini 2.5 Flash· LMArena data1,283.3
67Qwen3 VL 235B· LMArena data1,281.8
68GPT-5.5 Instant· LMArena data1,277.2
69Gemini 3.1 Flash Lite· LMArena data1,276.1
70Grok 4.7xHigh· LMArena data1,275
71GPT-6 LunaMax· LMArena data1,273.2
72GPT 5.1· LMArena data1,270.1
73GPT 5.2· LMArena data1,269.3
74GPT 5.1High· LMArena data1,268.9
75GPT-6 SolMax· LMArena data1,268.1
76ERNIE-5.0-Preview1220· LMArena data1,267.6
77GPT-5 Chat· LMArena data1,266.9
78GPT-5.2 Chat20260210· LMArena data1,261.8
79Grok 4.3· LMArena data1,255.7
80ChatGPT-4o Latest20250326· LMArena data1,253.9
81Grok 40709· LMArena data1,248.8
82Mistral Medium 3.5· LMArena data1,244.5
83Mistral Large 3· LMArena data1,242.8
84OpenAI o32025-04-16· LMArena data1,236.8
85NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,234.9
86o12024-12-17· LMArena data1,234.7
87GPT 5High· LMArena data1,234.6
88Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,233.4
89GPT 5.4 NanoHigh· LMArena data1,233
90Grok 4.1 FastReasoning· LMArena data1,233
91GPT 4.12025-04-14· LMArena data1,226.1
92Qwen3 VL 235Bthinking· LMArena data1,218.9
93o4 Mini2025-04-16· LMArena data1,218.2
94GLM 4.6v· LMArena data1,216.8
95GPT-5 miniHigh· LMArena data1,213.8
96Gemini 2.5 Flash-Lite PreviewThinking, 06-17· LMArena data1,193.6
97Mistral Medium 3.12508· LMArena data1,189.5
98Gemini 1.5 Pro002· LMArena data1,186.3
99GPT-4.1 mini2025-04-14· LMArena data1,185.5
100GPT-4.5 Preview2025-02-27· LMArena data1,175.5

Showing 51–100 of 135 results.

Data credits: LMArena, CC BY 4.0 (licence)