Skip to content

Benchmark

Arena ELO - Industry Life and Physical and Social Science

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

Models measured
364
Scores recorded
421
Sources
1
IQ weight
1.24

Score distribution

1,316.4
Mean
1,364.4
Median
158.9
Std dev
1,071.5
10th percentile
1,475.1
90th percentile
800.9
Min
800.91,549.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.24 for chat models, measured over 364 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Gemini 4 NeonHigh· LMArena data1,549.3
2Gemini 4 ArgonHigh· LMArena data1,549
3Claude Fable 5.1Max· LMArena data1,537
4Gemini 4 CarbonHigh· LMArena data1,536.8
5Claude Opus 5Max· LMArena data1,532.7
6Claude Opus 5.5High· LMArena data1,523.9
7Gemini 3.8 FlashHigh· LMArena data1,521.1
8Claude Opus 5High· LMArena data1,520.8
9Claude Opus 4.6High· LMArena data1,518.8
10Gemini 4 HydrogenHigh· LMArena data1,516.4
11Qwen3.8 Max· LMArena data1,513.2
12Gemini 3.7 FlashHigh· LMArena data1,511.8
13Claude Opus 4.6· LMArena data1,511.1
14Claude Opus 4.7High· LMArena data1,508
15Muse WonderMax· LMArena data1,507
16Claude Fable 5High· LMArena data1,506
17Muse Spark 1.3Max· LMArena data1,503.9
18MiMo V2.6 Pro· LMArena data1,503.9
19Muse Spark 1.2xHigh· LMArena data1,503.1
20GLM 5.3Max· LMArena data1,500
21Kimi K3Max· LMArena data1,499.4
22Qwen3.5-Max-Preview· LMArena data1,497.9
23Claude Opus 4.7· LMArena data1,497.6
24Gemini 3.1 Pro Preview· LMArena data1,496.1
25Gemini 3.5 FlashMedium· LMArena data1,495.4
26Claude Fable 5.2Max· LMArena data1,494.1
27Gemini 3.5 FlashHigh· LMArena data1,493.6
28Gemini 3.6 FlashHigh· LMArena data1,490.4
29GLM 5.2Max· LMArena data1,488.6
30GLM 5.3 Flash· LMArena data1,487.6
31GPT 5.5High· LMArena data1,484.9
32Gemini 3 Pro Preview· LMArena data1,484.9
33GPT 5.5· LMArena data1,484.6
34Muse Spark 1.1· LMArena data1,484.3
35ERNIE 5.1· LMArena data1,483.5
36MiMo V2.5 Pro· LMArena data1,481.7
37Qwen3.7 Max Preview· LMArena data1,480.6
38Gemini 2.5 Pro· LMArena data1,480.3
39Claude Sonnet 5.5xHigh· LMArena data1,479.4
40GLM 5.1· LMArena data1,478.7
41GPT 5.4High· LMArena data1,478.1
42Claude Opus 4.8High· LMArena data1,477.3
43Muse Spark· LMArena data1,475.1
44Claude Sonnet 4.6· LMArena data1,475.1
45Gemini 3 Flash· LMArena data1,473
46Claude Opus 4.8· LMArena data1,470.5
47DeepSeek V4.1 Flash 0910Max· LMArena data1,469.2
48Kimi K3.1 ProMax· LMArena data1,468.1
49DeepSeek V4 Pro· LMArena data1,468
50ERNIE-5.0-Preview1203· LMArena data1,467.7

Showing 1–50 of 421 results.

Data credits: LMArena, CC BY 4.0 (licence)