Skip to content

Benchmark

Arena ELO - Spanish

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

Models measured
259
Scores recorded
305
Sources
1
IQ weight
1.90

Score distribution

1,355.9
Mean
1,399.3
Median
117.6
Std dev
1,167.6
10th percentile
1,470
90th percentile
1,007
Min
1,0071,522.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.90 for chat models, measured over 259 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 Opus 5Max· LMArena data1,522.3
2Gemini 4 ArgonHigh· LMArena data1,516
3Claude Opus 5.5High· LMArena data1,514.2
4Claude Fable 5.1Max· LMArena data1,508.2
5Claude Opus 4.6· LMArena data1,507.1
6Claude Opus 5High· LMArena data1,506
7Gemini 4 NeonHigh· LMArena data1,505.4
8Claude Opus 4.6High· LMArena data1,503.7
9Claude Opus 4.7High· LMArena data1,495.1
10Muse Spark 1.3Max· LMArena data1,493.1
11Qwen3.8 Max· LMArena data1,491.6
12Claude Fable 5High· LMArena data1,488
13Gemini 4 HydrogenHigh· LMArena data1,487.3
14Gemini 3.8 FlashHigh· LMArena data1,485.4
15Gemini 3.7 FlashHigh· LMArena data1,484.6
16Kimi K3.1 ProMax· LMArena data1,484.3
17Muse Spark 1.2xHigh· LMArena data1,483.1
18GLM 5.2Max· LMArena data1,481.7
19Gemini 3.5 FlashHigh· LMArena data1,481
20Gemini 3.1 Pro Preview· LMArena data1,480
21Muse WonderMax· LMArena data1,480
22GLM 5.3 Flash· LMArena data1,478
23Kimi K3Max· LMArena data1,477
24Gemini 3.5 FlashMedium· LMArena data1,476.3
25Gemini 3.6 FlashHigh· LMArena data1,474.3
26Gemini 2.5 Pro· LMArena data1,473.6
27Claude Opus 4.7· LMArena data1,473.1
28GLM 5.3Max· LMArena data1,472.7
29ERNIE 5.1· LMArena data1,472.3
30ERNIE-5.0-Preview1203· LMArena data1,471.6
31Qwen3.5-Max-Preview· LMArena data1,470
32MiMo V2.5 Pro· LMArena data1,469.8
33GLM 5.1· LMArena data1,469.4
34Muse Spark· LMArena data1,469.4
35Gemini 3 Flash· LMArena data1,469.2
36Gemini 3 Pro Preview· LMArena data1,468.6
37GPT 5.5High· LMArena data1,468.2
38Claude Opus 4.8High· LMArena data1,467.8
39MiMo V2.6 Flash· LMArena data1,464.3
40Kimi K2.6· LMArena data1,463.8
41Muse Spark 1.1· LMArena data1,463.7
42Claude Sonnet 4.6· LMArena data1,462.7
43Qwen3 Max Preview· LMArena data1,462.4
44Doubao Seed 2.0 Pro· LMArena data1,462
45Nemotron 3 UltraNVFP4· LMArena data1,461.1
46Claude Sonnet 5.5xHigh· LMArena data1,460.6
47GPT 5.5· LMArena data1,458.5
48MiMo V2 Pro· LMArena data1,458.2
49Claude Opus 4.5High, 32K, 20251101· LMArena data1,457.5
50DeepSeek V4.1 Flash 0910Max· LMArena data1,456.9

Showing 1–50 of 305 results.

Data credits: LMArena, CC BY 4.0 (licence)