Skip to content

Benchmark

Arena ELO

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

Models measured
366
Scores recorded
423
Sources
1
IQ weight
1.19

Score distribution

1,312
Mean
1,354.8
Median
146.6
Std dev
1,084.5
10th percentile
1,462.5
90th percentile
833.5
Min
833.51,539.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.19 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
1Gemini 4 CarbonHigh· LMArena data1,539.3
2Gemini 4 ArgonHigh· LMArena data1,527.5
3Gemini 4 NeonHigh· LMArena data1,523.6
4Claude Opus 5.5High· LMArena data1,512.9
5Claude Fable 5.1Max· LMArena data1,512.5
6Claude Opus 5Max· LMArena data1,506.4
7Muse WonderMax· LMArena data1,503.3
8Claude Opus 5High· LMArena data1,502.2
9Gemini 4 HydrogenHigh· LMArena data1,501.8
10Claude Opus 4.6High· LMArena data1,501.5
11Gemini 3.8 FlashHigh· LMArena data1,500.2
12Claude Opus 4.6· LMArena data1,496.7
13Muse Spark 1.3Max· LMArena data1,493.6
14MiMo V2.6 Pro· LMArena data1,492.7
15Claude Fable 5High· LMArena data1,491.8
16Claude Opus 4.7High· LMArena data1,489.9
17Gemini 3.7 FlashHigh· LMArena data1,489.3
18Qwen3.8 Max· LMArena data1,485.3
19Muse Spark 1.2xHigh· LMArena data1,484
20Claude Opus 4.7· LMArena data1,483.4
21Gemini 3.5 FlashHigh· LMArena data1,483.1
22Gemini 3.1 Pro Preview· LMArena data1,480.1
23Gemini 3 Pro Preview· LMArena data1,479.5
24Gemini 3.6 FlashHigh· LMArena data1,479.5
25Muse Spark 1.1· LMArena data1,479.1
26Claude Fable 5.2Max· LMArena data1,478.3
27Gemini 3.5 FlashMedium· LMArena data1,477.7
28GLM 5.3Max· LMArena data1,475.4
29Kimi K3Max· LMArena data1,474.7
30Qwen3.7 Max Preview· LMArena data1,474.6
31Muse Spark· LMArena data1,474.3
32GLM 5.3 Flash· LMArena data1,471.4
33Qwen3.5-Max-Preview· LMArena data1,471.1
34GPT 5.5High· LMArena data1,470.9
35Claude Sonnet 5.5xHigh· LMArena data1,469.6
36GLM 5.2Max· LMArena data1,469.5
37GPT 5.4High· LMArena data1,469
38ERNIE 5.1· LMArena data1,468
39GPT 5.5· LMArena data1,466.2
40Gemini 3 Flash· LMArena data1,465.9
41MiMo V2.5 Pro· LMArena data1,463.9
42DeepSeek V4.1 Flash 0910Max· LMArena data1,463
43GLM 5.1· LMArena data1,462.5
44Claude Opus 4.8High· LMArena data1,461.5
45Gemini 2.5 Pro· LMArena data1,457.8
46Kimi K3.1 ProMax· LMArena data1,457.7
47Claude Sonnet 4.6· LMArena data1,457.7
48GPT-5.6 SolxHigh· LMArena data1,457.3
49Kimi K2.6· LMArena data1,455.4
50Qwen3.7 Plus· LMArena data1,454

Showing 1–50 of 423 results.

Data credits: LMArena, CC BY 4.0 (licence)