Skip to content

Benchmark

Arena ELO - English

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

Models measured
366
Scores recorded
423
Sources
1
IQ weight
1.26

Score distribution

1,327.7
Mean
1,373.1
Median
138.5
Std dev
1,119.5
10th percentile
1,468.7
90th percentile
845.9
Min
845.91,532
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.26 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 data1,532
2Gemini 4 ArgonHigh· LMArena data1,527.5
3Claude Opus 5.5High· LMArena data1,519
4Claude Opus 4.6High· LMArena data1,511.5
5Gemini 4 NeonHigh· LMArena data1,511.2
6Muse WonderMax· LMArena data1,509.3
7Claude Fable 5.1Max· LMArena data1,508.5
8Claude Opus 5Max· LMArena data1,507
9Claude Opus 4.6· LMArena data1,506.7
10MiMo V2.6 Pro· LMArena data1,503.2
11Claude Opus 5High· LMArena data1,502.2
12Claude Fable 5High· LMArena data1,499
13Gemini 3.8 FlashHigh· LMArena data1,498.8
14Gemini 4 HydrogenHigh· LMArena data1,496.8
15Claude Opus 4.7High· LMArena data1,496.2
16Muse Spark 1.3Max· LMArena data1,495.5
17Qwen3.8 Max· LMArena data1,493.9
18Claude Opus 4.7· LMArena data1,487.8
19Gemini 3.7 FlashHigh· LMArena data1,484.9
20Muse Spark 1.2xHigh· LMArena data1,484.5
21GLM 5.3Max· LMArena data1,483
22Gemini 3.6 FlashHigh· LMArena data1,480.6
23Gemini 3.5 FlashHigh· LMArena data1,480.5
24Muse Spark· LMArena data1,480.5
25Kimi K3Max· LMArena data1,479.1
26Claude Sonnet 5.5xHigh· LMArena data1,478.7
27Muse Spark 1.1· LMArena data1,478.6
28Gemini 3.1 Pro Preview· LMArena data1,478.3
29ERNIE 5.1· LMArena data1,477.6
30Gemini 3 Pro Preview· LMArena data1,477.6
31MiMo V2.5 Pro· LMArena data1,476.8
32GLM 5.3 Flash· LMArena data1,476.8
33Qwen3.5-Max-Preview· LMArena data1,476.3
34Gemini 3.5 FlashMedium· LMArena data1,475.8
35GLM 5.1· LMArena data1,475.7
36GLM 5.2Max· LMArena data1,474.8
37Claude Fable 5.2Max· LMArena data1,473.6
38DeepSeek V4.1 Flash 0910Max· LMArena data1,473
39Claude Sonnet 4.6· LMArena data1,472.5
40MiMo V2.6 Flash· LMArena data1,472.2
41GPT 5.5High· LMArena data1,470.2
42Qwen3.7 Max Preview· LMArena data1,470
43Claude Opus 4.8High· LMArena data1,468.7
44GPT 5.5· LMArena data1,468.4
45Kimi K3.1 ProMax· LMArena data1,468
46Gemini 3 Flash· LMArena data1,467.5
47GPT 5.4High· LMArena data1,467.1
48Claude Opus 4.520251101· LMArena data1,460.9
49Kimi K2.6· LMArena data1,460.1
50Claude Opus 4.8· LMArena data1,459.8

Showing 1–50 of 423 results.

Data credits: LMArena, CC BY 4.0 (licence)