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
201Mistral Small 3.22506· LMArena data1,347.6
202Command A03-2025· LMArena data1,347.5
203o4 Mini2025-04-16· LMArena data1,346.2
204o12024-12-17· LMArena data1,344.8
205Olmo 3.1 32B Instruct· LMArena data1,337.1
206GLM 4.5V· LMArena data1,333.4
207Kimi K2 Preview0711· LMArena data1,330
208Trinity Large Thinking· LMArena data1,327.5
209MiniMax M2· LMArena data1,326.2
210o3 MiniHigh· LMArena data1,320.9
211GPT-4.1 mini2025-04-14· LMArena data1,319.3
212Qwen3 30B A3B· LMArena data1,316.8
213Yi Lightning· LMArena data1,315.1
214Gemini 2.0 Flash-Lite Preview02-05· LMArena data1,313.2
215GLM 4 Plus· LMArena data1,310.4
216Gemini 1.5 Pro002· LMArena data1,310.2
217o3 Mini· LMArena data1,309
218Gemma 3n E4B IT· LMArena data1,305.2
219O1 Mini· LMArena data1,302.5
220O1 Preview· LMArena data1,301.6
221Claude Sonnet 3.7Thinking 32K, 20250219· LMArena data1,298.6
222Llama 4 Maverick· LMArena data1,292.1
223GPT 4o2024-05-13· LMArena data1,291.9
224Claude Sonnet 3.720250219· LMArena data1,290
225Qwen Max0919· LMArena data1,289.7
226Claude 3.5 Sonnet20240620· LMArena data1,289.2
227Olmo 3.1 32B Think· LMArena data1,288.9
228Claude 3.5 Sonnet20241022· LMArena data1,285.4
229Mistral Small 3.1 24B Instruct2503· LMArena data1,283.8
230Grok 22024-08-13· LMArena data1,280.9
231Grok 2 mini2024-08-13· LMArena data1,278.3
232Llama 4 Scout· LMArena data1,278
233GPT-4o mini2024-07-18· LMArena data1,275.8
234Athene V2 Chat· LMArena data1,274.1
235Magistral Medium2506· LMArena data1,270.5
236GPT 4o2024-08-06· LMArena data1,268.6
237Llama 3.3 70B Instruct· LMArena data1,268.4
238GPT OSS 20b· LMArena data1,268.3
239Mistral Large2411· LMArena data1,267.7
240Claude Haiku 3.520241022· LMArena data1,261.2
241GPT-4 Turbo Preview1106· LMArena data1,260.7
242GPT-4 Turbo2024-04-09· LMArena data1,259.7
243Llama 3.1 405B InstructBF16· LMArena data1,259.5
244Athene 70B0725· LMArena data1,259
245Granite 4.0 H Small· LMArena data1,257.7
246Qwen2.5 72B Instruct· LMArena data1,255.2
247Llama 3.1 70B Instruct· LMArena data1,252.8
248Llama 3.1 405B InstructFP8· LMArena data1,252.7
249DeepSeek V2.5· LMArena data1,247.8
250GPT-4 Turbo Preview0125· LMArena data1,247.2

Showing 201–250 of 305 results.

Data credits: LMArena, CC BY 4.0 (licence)