Skip to content

Benchmark

Arena ELO Vision - Humor

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

Models measured
90
Scores recorded
102
Sources
1
IQ weight
1.76

Score distribution

1,244.3
Mean
1,252.6
Median
54.3
Std dev
1,167.5
10th percentile
1,313
90th percentile
1,100.3
Min
1,100.31,347.9
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.76 for chat models, measured over 90 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51Gemini 2.5 Flash Preview09-2025· LMArena data1,252.6
52MiMo V2.6 Flash· LMArena data1,251.5
53Claude Sonnet 4.6· LMArena data1,251.1
54ChatGPT-4o Latest20250326· LMArena data1,247.9
55GPT-5.6 SolxHigh· LMArena data1,246.3
56Qwen3.5 122B-A10B· LMArena data1,244.5
57GPT-5.6 TerraxHigh· LMArena data1,243.6
58Qwen 3.8 27B· LMArena data1,242
59Grok 4.1 FastReasoning· LMArena data1,241.1
60GPT-5.2 Chat20260210· LMArena data1,238.6
61GPT-5.4 miniHigh· LMArena data1,237.5
62MiniMax M3· LMArena data1,233.4
63Kimi K2.5Instant· LMArena data1,228.6
64Qwen3.5 27B· LMArena data1,227.9
65GPT 5.2High· LMArena data1,227.2
66MiMo V2.5· LMArena data1,226.6
67GPT 5.1High· LMArena data1,224.5
68Gemini 2.5 Flash· LMArena data1,224.4
69Grok 4.3· LMArena data1,222.9
70OpenAI o32025-04-16· LMArena data1,222
71GPT-5 Chat· LMArena data1,218.2
72Mistral Medium 3.5· LMArena data1,217.7
73Mistral Large 3· LMArena data1,216.9
74Step 5 Preview· LMArena data1,214.9
75Grok 4.7xHigh· LMArena data1,213.3
76Qwen3 VL 235B· LMArena data1,207.6
77Grok 40709· LMArena data1,207.4
78GPT 5High· LMArena data1,206.3
79GPT-5 miniHigh· LMArena data1,204.8
80Inkling Small· LMArena data1,199
81o4 Mini2025-04-16· LMArena data1,198.9
82GPT 5.2· LMArena data1,198.2
83GPT 4.12025-04-14· LMArena data1,195.2
84GPT-5.6 LunaxHigh· LMArena data1,192.8
85ERNIE-5.0-Preview1220· LMArena data1,191.7
86NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,188.5
87MiMo V2 Omni· LMArena data1,187.1
88Gemini 2.5 Flash-Lite PreviewThinking, 06-17· LMArena data1,186.1
89GPT-4.1 mini2025-04-14· LMArena data1,181.5
90GPT-6 SolMax· LMArena data1,173.4
91Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,167.7
92Mistral Medium 3.12508· LMArena data1,167.5
93GPT-6 LunaMax· LMArena data1,166.7
94Gemma 3 27B IT· LMArena data1,165
95Gemini 2.0 Flash001· LMArena data1,161.4
96GPT 5.4 NanoHigh· LMArena data1,161.2
97Mistral Medium 32505· LMArena data1,144.1
98Mistral Small 3.1 24B Instruct2503· LMArena data1,141.2
99Mistral Small 3.22506· LMArena data1,138.8
100GPT-5 nanoHigh· LMArena data1,109.5

Showing 51–100 of 102 results.

Data credits: LMArena, CC BY 4.0 (licence)