Skip to content

Benchmark

Arena ELO - Industry Software and It Services

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

Models measured
366
Scores recorded
423
Sources
1
IQ weight
1.29

Score distribution

1,322.6
Mean
1,374.8
Median
161.3
Std dev
1,081.5
10th percentile
1,486.1
90th percentile
719.3
Min
719.31,552.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.29 for chat models, measured over 366 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51Claude Opus 4.8· LMArena data1,481.7
52GPT-6.1 SolMax· LMArena data1,481.4
53nova-experimental-chat26-02-10· LMArena data1,481.1
54GPT-5.6 TerraxHigh· LMArena data1,481
55GPT-6 AstraMax· LMArena data1,479.6
56GPT 5.4· LMArena data1,475.2
57Qwen 3.8 27B· LMArena data1,475
58Doubao Seed 2.0 Pro· LMArena data1,474.6
59Claude Sonnet 5High· LMArena data1,473.5
60Claude Sonnet 4.520250929· LMArena data1,472.7
61Qwen3.7 Plus· LMArena data1,472.4
62Step 5 Preview· LMArena data1,471.6
63Grok 4.5· LMArena data1,471
64Kimi K2.5Instant· LMArena data1,470.8
65Gemini 3 Flash· LMArena data1,470.7
66Claude Sonnet 4.5High, 32K, 20250929· LMArena data1,470.7
67Kimi K2.5Thinking· LMArena data1,469
68DeepSeek V4 Pro· LMArena data1,468.6
69MiMo V2 Pro· LMArena data1,468.1
70Nemotron 3 UltraNVFP4· LMArena data1,468.1
71Inkling FP4· LMArena data1,466.2
72Qwen3.6 Max Preview· LMArena data1,465.3
73LongCat-Flash-Chat Exp2602· LMArena data1,464.2
74Hy3 (Deep Infra)· LMArena data1,463.8
75GPT-5.6 LunaxHigh· LMArena data1,463.7
76MiMo V2.5· LMArena data1,463.6
77MiniMax M3· LMArena data1,463.5
78Gemma 4 31B IT· LMArena data1,462.9
79GPT-6.1 TerraMax· LMArena data1,462.2
80ERNIE 5.00110· LMArena data1,462.2
81Qwen3.5 397B A17B· LMArena data1,462
82Qwen3.6 Plus· LMArena data1,462
83Grok 4.20Reasoning, 0309, beta· LMArena data1,461.4
84Grok 4.20 Multi-Agent0309, beta· LMArena data1,461.3
85Beam 1.0 501B A23B· LMArena data1,460.6
86GLM 5· LMArena data1,460.3
87DeepSeek V4 ProHigh, 20260813· LMArena data1,459.7
88Mistral Large 4· LMArena data1,459.2
89Gemini 2.5 Pro· LMArena data1,459
90Qwen3 Max Preview· LMArena data1,458.7
91Mistral Medium 3.5· LMArena data1,458.5
92LongCat Flash Chat· LMArena data1,457.8
93DeepSeek-V4-Pro PreviewHigh· LMArena data1,456.7
94Claude Opus 4.1Thinking 16K, 20250805· LMArena data1,456.3
95MiMo V2 Omni· LMArena data1,455.9
96GLM 4.6· LMArena data1,455.4
97Grok 4.6High· LMArena data1,454.4
98Gemma 4 26B A4B· LMArena data1,454.3
99GPT-5.2 Chat20260210· LMArena data1,454.3
100GPT 5.1High· LMArena data1,453.7

Showing 51–100 of 423 results.

Data credits: LMArena, CC BY 4.0 (licence)