Skip to content

Benchmark

Arena ELO Text Factuality - Spanish

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

Models measured
86
Scores recorded
99
Sources
1
IQ weight
1.96

Score distribution

1,446.3
Mean
1,448.2
Median
24.9
Std dev
1,416.6
10th percentile
1,476.7
90th percentile
1,371.3
Min
1,371.31,500.2
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.96 for chat models, measured over 86 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 4.6· LMArena data1,500.2
2Claude Opus 5Max· LMArena data1,492.8
3Claude Opus 4.7High· LMArena data1,487.3
4Claude Opus 4.6High· LMArena data1,486.6
5Gemini 3 Pro Preview· LMArena data1,484.7
6Gemini 4 ArgonHigh· LMArena data1,484.4
7GPT 5.5High· LMArena data1,480.6
8Gemini 3.8 FlashHigh· LMArena data1,480.3
9Claude Opus 5High· LMArena data1,479.8
10Gemini 3.6 FlashHigh· LMArena data1,476.9
11GLM 5.2Max· LMArena data1,476.7
12Claude Fable 5High· LMArena data1,476.6
13Qwen3.8 Max· LMArena data1,475.5
14Gemini 3.1 Pro Preview· LMArena data1,473
15Gemini 3.5 FlashMedium· LMArena data1,473
16Gemini 3.5 FlashHigh· LMArena data1,472.4
17Claude Opus 4.7· LMArena data1,471.5
18Claude Opus 4.8High· LMArena data1,470.7
19Gemini 2.5 Pro· LMArena data1,470.1
20Grok 4.5· LMArena data1,469.5
21GPT-5.6 TerraxHigh· LMArena data1,469.4
22Kimi K3Max· LMArena data1,469.1
23Gemini 3.7 FlashHigh· LMArena data1,468.3
24GPT 5.4· LMArena data1,466.2
25GPT-5.6 SolxHigh· LMArena data1,465.7
26Muse Spark 1.3Max· LMArena data1,465.5
27GPT-5.6 LunaxHigh· LMArena data1,464.3
28MiMo V2.5 Pro· LMArena data1,464.2
29GPT 5.4High· LMArena data1,461.9
30Muse Spark 1.2xHigh· LMArena data1,461.4
31GPT-6 AstraMax· LMArena data1,460.8
32GPT 5.5· LMArena data1,459.7
33ERNIE 5.1· LMArena data1,457.8
34DeepSeek V4 Pro· LMArena data1,457.6
35GLM 5.3 Flash· LMArena data1,457.5
36Claude Sonnet 4.520250929· LMArena data1,457.1
37Inkling FP4· LMArena data1,456.7
38Claude Sonnet 4.6· LMArena data1,456.6
39GLM 5.1· LMArena data1,455.9
40Claude Opus 4.8· LMArena data1,455.1
41Kimi K2.6· LMArena data1,454.6
42Qwen3.7 Plus· LMArena data1,454.5
43Muse Spark 1.1· LMArena data1,454.3
44Claude Opus 4.5High, 32K, 20251101· LMArena data1,452
45GLM 5.3Max· LMArena data1,451.9
46ERNIE 5.00110· LMArena data1,450.6
47Claude Opus 4.520251101· LMArena data1,449.6
48DeepSeek-V4-Pro PreviewHigh· LMArena data1,449.5
49Grok 4.20 Multi-Agent0309, beta· LMArena data1,448.4
50MiMo V2.6 Flash· LMArena data1,448.2

Showing 1–50 of 99 results.

Data credits: LMArena, CC BY 4.0 (licence)