Skip to content

Benchmark

Arena ELO - German

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

Models measured
273
Scores recorded
319
Sources
1
IQ weight
1.52

Score distribution

1,328.6
Mean
1,372.1
Median
138.3
Std dev
1,110.8
10th percentile
1,469.8
90th percentile
901.9
Min
901.91,585.2
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.52 for chat models, measured over 273 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101OpenAI o32025-04-16· LMArena data1,419.8
102Qwen3 VL 235Bthinking· LMArena data1,419.7
103MiMo V2.5· LMArena data1,419.3
104Gemini 2.5 Flash Preview09-2025· LMArena data1,418
105Gemini 2.5 Flash· LMArena data1,417.7
106DeepSeek-V4-Flash PreviewHigh· LMArena data1,417.4
107GPT 5.1· LMArena data1,417.1
108Qwen3 Next 80B A3B Instruct· LMArena data1,417
109Grok 4.6High· LMArena data1,416.9
110DeepSeek V4 Flash· LMArena data1,416.6
111GPT 5High· LMArena data1,416
112MiMo V2 Pro· LMArena data1,413.1
113Claude Opus 4.1Thinking 16K, 20250805· LMArena data1,413.1
114DeepSeek V3.1· LMArena data1,411.9
115Kimi K2.5Instant· LMArena data1,411.9
116DeepSeek V3.2Thinking· LMArena data1,411.9
117GPT-5.5 Instant· LMArena data1,410.3
118GPT-5.4 miniHigh· LMArena data1,408.5
119DeepSeek V3.2· LMArena data1,408.5
120Qwen 3 235B A22B2507, thinking· LMArena data1,408.2
121LongCat Flash Chat· LMArena data1,407.7
122DeepSeek V3.1Thinking· LMArena data1,407.4
123GLM 4.5· LMArena data1,406.7
124Claude Opus 4.120250805· LMArena data1,405
125DeepSeek R10528· LMArena data1,404.9
126GPT-5 Chat· LMArena data1,404.3
127Step 3.5 Flash· LMArena data1,403
128Grok 4.1 FastReasoning· LMArena data1,402.9
129MiMo V2 Omni· LMArena data1,401.9
130Inkling Small· LMArena data1,401.7
131MiniMax M2.7· LMArena data1,398
132Grok 4.3· LMArena data1,396.5
133nova-experimental-chat11-10· LMArena data1,395.5
134Qwen3.5 27B· LMArena data1,395.3
135MiMo V2 FlashThinking· LMArena data1,394.9
136nova-experimental-chat10-20· LMArena data1,392.5
137Claude Opus 4Thinking 16K, 20250514· LMArena data1,390.9
138Kimi K2 Thinking· LMArena data1,390
139Qwen3.5 Flash· LMArena data1,389.7
140Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,388.4
141GPT-6 SolMax· LMArena data1,388.2
142Qwen 3 235B A22B· LMArena data1,387
143Kimi K2 Preview0905· LMArena data1,386.7
144GPT-5.3 Chat· LMArena data1,384.9
145MiMo V2 FlashNon-Thinking· LMArena data1,384.6
146DeepSeek R1· LMArena data1,384.4
147Qwen 3 235B A22BNon-Thinking· LMArena data1,382.3
148Grok 4 FastReasoning· LMArena data1,381.9
149GPT-6 LunaMax· LMArena data1,381.2
150MiniMax-M2.1 Preview· LMArena data1,381.2

Showing 101–150 of 319 results.

Data credits: LMArena, CC BY 4.0 (licence)