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
51Claude Sonnet 4.520250929· LMArena data1,456.9
52DeepSeek V4 Pro· LMArena data1,456.1
53Mistral Large 4· LMArena data1,455.8
54Qwen3.7 Plus· LMArena data1,455.4
55Hy3 (Deep Infra)· LMArena data1,455
56Qwen3.6 Max Preview· LMArena data1,454.1
57Inkling FP4· LMArena data1,453.9
58Claude Opus 4.8· LMArena data1,453.9
59GLM 4.5· LMArena data1,453.9
60GLM 5· LMArena data1,453.5
61GPT 5.4High· LMArena data1,452.6
62Claude Opus 4.520251101· LMArena data1,452.5
63GPT 5.4· LMArena data1,452.1
64Grok 4.5· LMArena data1,451.6
65ERNIE 5.00110· LMArena data1,449.1
66GPT-5.6 TerraxHigh· LMArena data1,449
67DeepSeek-V4-Pro PreviewHigh· LMArena data1,449
68Kimi K2.5Thinking· LMArena data1,448.5
69Claude Opus 4.120250805· LMArena data1,448.3
70GPT-5.6 LunaxHigh· LMArena data1,448.2
71Grok 4.20 Multi-Agent0309, beta· LMArena data1,447.3
72Claude Fable 5.2Max· LMArena data1,446.1
73Kimi K2.5Instant· LMArena data1,445.7
74Claude Opus 4.1Thinking 16K, 20250805· LMArena data1,445.5
75Step 5 Preview· LMArena data1,445.5
76Qwen 3.8 27B· LMArena data1,445.4
77LongCat Flash Chat· LMArena data1,444.9
78Qwen3.5 397B A17B· LMArena data1,444.6
79GPT-5.6 SolxHigh· LMArena data1,444.3
80nova-experimental-chat11-10· LMArena data1,443.7
81Grok 4.20Reasoning, 0309, beta· LMArena data1,443
82Gemma 4 31B IT· LMArena data1,442.7
83Claude Sonnet 4.5High, 32K, 20250929· LMArena data1,442.5
84Claude Sonnet 5High· LMArena data1,441.9
85DeepSeek V3.2 Exp· LMArena data1,441
86Gemini 3.5 Flash Lite· LMArena data1,440.2
87GPT-6 AstraMax· LMArena data1,439.4
88GPT-6.1 SolMax· LMArena data1,438
89Grok 4.1Thinking· LMArena data1,437.7
90MiMo V2 Omni· LMArena data1,437.5
91DeepSeek V4 ProHigh, 20260813· LMArena data1,436.7
92GLM 4.6· LMArena data1,436.7
93Grok 4.20 Beta 1· LMArena data1,436.6
94Mistral Large 3· LMArena data1,436.5
95Inkling Small· LMArena data1,435.6
96DeepSeek V4 Flash· LMArena data1,434.8
97Qwen3 Next 80B A3B Instruct· LMArena data1,434.1
98ChatGPT-4o Latest20250326· LMArena data1,434
99GLM 4.7· LMArena data1,433.5
100Mistral Medium 3.12508· LMArena data1,433.5

Showing 51–100 of 305 results.

Data credits: LMArena, CC BY 4.0 (licence)