Skip to content

Benchmark

Arena ELO - Japanese

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

Models measured
245
Scores recorded
286
Sources
1
IQ weight
1.65

Score distribution

1,296.5
Mean
1,336.3
Median
150
Std dev
1,061.5
10th percentile
1,461.1
90th percentile
878.3
Min
878.31,557.4
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.65 for chat models, measured over 245 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
151MiMo V2 FlashNon-Thinking· LMArena data1,325
152DeepSeek R1· LMArena data1,324.4
153Qwen3.5 35B A3B· LMArena data1,322.5
154GPT 4.12025-04-14· LMArena data1,319.1
155Grok 3 MiniHigh· LMArena data1,317.5
156Mistral Medium 32505· LMArena data1,315.8
157MiMo V2 Omni· LMArena data1,314.7
158Qwen 3 235B A22B· LMArena data1,311.5
159Qwen3 Coder· LMArena data1,310.8
160o4 Mini2025-04-16· LMArena data1,308.5
161Trinity Large Thinking· LMArena data1,308.2
162MiMo V2.5· LMArena data1,307.2
163Claude Sonnet 420250514· LMArena data1,301.9
164Gemini 2.0 Flash-Lite Preview02-05· LMArena data1,301.7
165Llama 3.3 Nemotron Super 49B v1.5· LMArena data1,300.7
166Qwen2.5-Max· LMArena data1,299.4
167O1 Preview· LMArena data1,294.7
168Gemini 2.0 Flash001· LMArena data1,293.8
169Gemini 1.5 Pro002· LMArena data1,292.6
170Trinity Large Preview· LMArena data1,292.6
171GPT-4.1 mini2025-04-14· LMArena data1,289.9
172Claude Sonnet 4Thinking 32K, 20250514· LMArena data1,287.4
173Gemma 3 27B IT· LMArena data1,287
174o3 MiniHigh· LMArena data1,285.8
175MiniMax-M2.1 Preview· LMArena data1,285.6
176Command A03-2025· LMArena data1,285.4
177Qwen3 Next 80B A3Bthinking· LMArena data1,280.5
178Mistral Small 3.22506· LMArena data1,275.6
179Nova 2 Lite· LMArena data1,273.5
180Gemma 3n E4B IT· LMArena data1,272
181Claude Sonnet 3.7Thinking 32K, 20250219· LMArena data1,266.8
182DeepSeek V3· LMArena data1,266.5
183Nemotron 3 Nano 30B A3BBF16· LMArena data1,265.8
184o3 Mini· LMArena data1,265
185QwQ 32B· LMArena data1,262.3
186Claude Sonnet 3.720250219· LMArena data1,260.5
187GPT 4o2024-05-13· LMArena data1,257
188Qwen3 30B A3B· LMArena data1,254.4
189Gemini 1.5 Flash002· LMArena data1,252.6
190MiniMax M2.7· LMArena data1,252.2
191Qwen Plus0125· LMArena data1,251.3
192O1 Mini· LMArena data1,245.1
193GPT OSS 20b· LMArena data1,244.6
194Grok 22024-08-13· LMArena data1,244.4
195Nemotron 3.5 Lightning 30B A3BNVFP4· LMArena data1,242.5
196Gemini Advanced0514· LMArena data1,242
197Gemini 1.5 Pro001· LMArena data1,239.2
198GPT 4o2024-08-06· LMArena data1,234.4
199Claude 3.5 Sonnet20241022· LMArena data1,234.2
200Claude 3.5 Sonnet20240620· LMArena data1,231

Showing 151–200 of 286 results.

Data credits: LMArena, CC BY 4.0 (licence)