Skip to content

Benchmark

Arena ELO - Japanese

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

Models measured
245
Scores recorded
286
Sources
1
IQ weight
1.65

Score distribution

1,296.5
Mean
1,336.3
Median
150
Std dev
1,061.5
10th percentile
1,461.1
90th percentile
878.3
Min
878.31,557.4
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.65 for chat models, measured over 245 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude Fable 5.1Max· LMArena data1,557.4
2Claude Opus 5.5High· LMArena data1,533.6
3Gemini 4 ArgonHigh· LMArena data1,532.1
4Gemini 3.8 FlashHigh· LMArena data1,522.2
5Claude Opus 5Max· LMArena data1,522.2
6Gemini 3.7 FlashHigh· LMArena data1,518.3
7Claude Opus 5High· LMArena data1,515.7
8Gemini 3 Pro Preview· LMArena data1,508.3
9Claude Fable 5High· LMArena data1,505.1
10GPT 5.5High· LMArena data1,502.1
11Muse WonderMax· LMArena data1,498.8
12Kimi K3Max· LMArena data1,498.7
13Gemini 3.1 Pro Preview· LMArena data1,494.6
14Qwen3.5-Max-Preview· LMArena data1,494.1
15Muse Spark 1.2xHigh· LMArena data1,492.7
16Gemini 3.5 FlashHigh· LMArena data1,491.1
17Gemini 3 Flash· LMArena data1,490.9
18Claude Opus 4.6High· LMArena data1,490.5
19Muse Spark 1.3Max· LMArena data1,490.4
20GPT 5.4High· LMArena data1,483.6
21GPT 5.5· LMArena data1,479.7
22Claude Opus 4.7High· LMArena data1,474.3
23GLM 5.3Max· LMArena data1,474
24Gemini 3.6 FlashHigh· LMArena data1,474
25Claude Opus 4.6· LMArena data1,472.5
26Claude Sonnet 5.5xHigh· LMArena data1,472.2
27GPT-5.6 SolxHigh· LMArena data1,470.3
28Qwen3.8 Max· LMArena data1,467.3
29Claude Opus 4.7· LMArena data1,461.1
30Gemini 2.5 Pro· LMArena data1,460.7
31Gemini 3.5 FlashMedium· LMArena data1,459.6
32GPT 5.1High· LMArena data1,454.7
33GLM 5.2Max· LMArena data1,452.8
34Muse Spark 1.1· LMArena data1,450.8
35GLM 5.3 Flash· LMArena data1,449.9
36Grok 4.20 Beta 1· LMArena data1,449.4
37GPT 5.4· LMArena data1,448.3
38GPT-5.6 TerraxHigh· LMArena data1,445.9
39DeepSeek V4 Pro· LMArena data1,444.1
40Claude Opus 4.8· LMArena data1,443.1
41Kimi K2.6· LMArena data1,442.4
42Claude Opus 4.8High· LMArena data1,441.4
43Inkling FP4· LMArena data1,441
44GLM 5.1· LMArena data1,439.5
45GLM 4.7· LMArena data1,438.7
46GPT-6.1 SolMax· LMArena data1,434.1
47Grok 4.5· LMArena data1,432.9
48DeepSeek V4.1 Flash 0910Max· LMArena data1,432.1
49Gemini 3.5 Flash Lite· LMArena data1,429.2
50Qwen3.5 397B A17B· LMArena data1,427.6

Showing 1–50 of 286 results.

Data credits: LMArena, CC BY 4.0 (licence)