Skip to content

Benchmark

Arena ELO - Non English

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

Models measured
366
Scores recorded
423
Sources
1
IQ weight
1.20

Score distribution

1,288.7
Mean
1,334.4
Median
160.8
Std dev
1,032.5
10th percentile
1,449.6
90th percentile
781.3
Min
781.31,534.5
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.20 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 data1,534.5
2Gemini 4 NeonHigh· LMArena data1,524.1
3Gemini 4 ArgonHigh· LMArena data1,520.9
4Claude Fable 5.1Max· LMArena data1,507
5Claude Opus 5.5High· LMArena data1,503.5
6Claude Opus 5Max· LMArena data1,499.9
7Claude Opus 5High· LMArena data1,495.4
8Gemini 4 HydrogenHigh· LMArena data1,494.9
9Gemini 3.8 FlashHigh· LMArena data1,493
10Muse WonderMax· LMArena data1,492.2
11Claude Opus 4.6High· LMArena data1,487.3
12Gemini 3.7 FlashHigh· LMArena data1,486
13Muse Spark 1.3Max· LMArena data1,484.3
14Claude Opus 4.6· LMArena data1,484.2
15Claude Fable 5High· LMArena data1,481.8
16Claude Opus 4.7High· LMArena data1,480.8
17Gemini 3.5 FlashHigh· LMArena data1,476.9
18Muse Spark 1.2xHigh· LMArena data1,476.7
19MiMo V2.6 Pro· LMArena data1,476.3
20Gemini 3.1 Pro Preview· LMArena data1,476
21Qwen3.8 Max· LMArena data1,475.2
22Gemini 3 Pro Preview· LMArena data1,474.5
23Claude Opus 4.7· LMArena data1,474.3
24Claude Fable 5.2Max· LMArena data1,473.8
25Qwen3.7 Max Preview· LMArena data1,472.8
26Gemini 3.5 FlashMedium· LMArena data1,472
27Muse Spark 1.1· LMArena data1,472
28Gemini 3.6 FlashHigh· LMArena data1,470.7
29GPT 5.5High· LMArena data1,466.2
30Qwen3.5-Max-Preview· LMArena data1,465.9
31Kimi K3Max· LMArena data1,465.3
32GPT 5.4High· LMArena data1,464.7
33Muse Spark· LMArena data1,463.9
34GLM 5.3Max· LMArena data1,463.2
35GLM 5.3 Flash· LMArena data1,461.1
36GPT 5.5· LMArena data1,458.9
37Gemini 3 Flash· LMArena data1,458.7
38GLM 5.2Max· LMArena data1,458.1
39Claude Sonnet 5.5xHigh· LMArena data1,454.9
40ERNIE 5.1· LMArena data1,454.6
41Gemini 2.5 Pro· LMArena data1,451.7
42Claude Opus 4.8High· LMArena data1,450.7
43GPT-5.6 SolxHigh· LMArena data1,449.6
44DeepSeek V4.1 Flash 0910Max· LMArena data1,449.6
45GLM 5.1· LMArena data1,448.4
46MiMo V2.5 Pro· LMArena data1,448.1
47GPT 5.4· LMArena data1,448.1
48Kimi K3.1 ProMax· LMArena data1,446.4
49Kimi K2.6· LMArena data1,446.2
50Qwen3.7 Plus· LMArena data1,444.3

Showing 1–50 of 423 results.

Data credits: LMArena, CC BY 4.0 (licence)