Skip to content

Benchmark

Arena ELO - English

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

Models measured
366
Scores recorded
423
Sources
1
IQ weight
1.26

Score distribution

1,327.7
Mean
1,373.1
Median
138.5
Std dev
1,119.5
10th percentile
1,468.7
90th percentile
845.9
Min
845.91,532
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.26 for chat models, measured over 366 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
151GPT-6.2 AstraMax· LMArena data1,417.5
152Step 3.5 Flash· LMArena data1,416.7
153OpenAI o32025-04-16· LMArena data1,416.4
154nova-experimental-chat10-20· LMArena data1,415.6
155Solar Pro 4· LMArena data1,414.9
156Claude Haiku 4.520251001· LMArena data1,414.3
157Grok 4 FastNon-Reasoning· LMArena data1,413.8
158Gemini 3.1 Flash Lite· LMArena data1,413.6
159Gemini 2.5 Flash Preview09-2025· LMArena data1,412.8
160GPT 5.2· LMArena data1,412.1
161GPT-5.4 miniHigh· LMArena data1,412
162MiMo V2 FlashThinking· LMArena data1,412
163GPT 5High· LMArena data1,409.1
164Grok 4.7xHigh· LMArena data1,408.7
165nova-experimental-chat26-01-10· LMArena data1,408.1
166Qwen3.5 35B A3B· LMArena data1,407.3
167Grok 4 FastReasoning· LMArena data1,406.6
168GPT-5 Chat· LMArena data1,405.7
169Claude Haiku 5.5High· LMArena data1,404.6
170Qwen3.5 Flash· LMArena data1,404.5
171Grok 4.3· LMArena data1,404
172MiniMax-M2.1 Preview· LMArena data1,402.3
173Nemotron 3 Super 120B A12B· LMArena data1,399.7
174GPT-6 SolMax· LMArena data1,397.6
175GLM 4.5 Air· LMArena data1,397.5
176Hunyuan T120250711· LMArena data1,396.9
177Qwen 3 235B A22BNon-Thinking· LMArena data1,396.7
178GLM 4.6v· LMArena data1,394.6
179Qwen3 Next 80B A3Bthinking· LMArena data1,392.5
180GPT 4.12025-04-14· LMArena data1,392.5
181GPT-6 LunaMax· LMArena data1,392.1
182Qwen3 30B A3B Instruct2507· LMArena data1,391.1
183GPT-5.3 Chat· LMArena data1,390.5
184DeepSeek V30324· LMArena data1,388.9
185Hunyuan TurboS20250416· LMArena data1,386.4
186Muse Glimmer· LMArena data1,386.1
187Claude Opus 4Thinking 16K, 20250514· LMArena data1,385.7
188Ling Flash 2.0· LMArena data1,385.4
189DeepSeek R1· LMArena data1,385.1
190Nova 2 Lite· LMArena data1,384.8
191Mistral Medium 32505· LMArena data1,384.5
192Granite 4.2 30B· LMArena data1,383.9
193nova-experimental-chat10-09· LMArena data1,383.7
194Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,382.8
195O1 Preview· LMArena data1,382.7
196GPT 5.4 NanoHigh· LMArena data1,380.8
197INTELLECT-3· LMArena data1,380.2
198MiniMax M2.5· LMArena data1,379.6
199GPT-5 miniHigh· LMArena data1,379.4
200Grok 3 MiniHigh· LMArena data1,379

Showing 151–200 of 423 results.

Data credits: LMArena, CC BY 4.0 (licence)