Skip to content

Benchmark

Arena ELO Text Factuality - Non English

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

Models measured
168
Scores recorded
192
Sources
1
IQ weight
2.36

Score distribution

1,422.4
Mean
1,430.7
Median
42.6
Std dev
1,361
10th percentile
1,469
90th percentile
1,245.6
Min
1,245.61,512.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.36 for chat models, measured over 168 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
151Qwen3.5 27B· LMArena data1,400.1
152Claude Haiku 4.520251001· LMArena data1,399.5
153Qwen3.5 Flash· LMArena data1,399.5
154Grok 4 FastReasoning· LMArena data1,399.3
155Step 3.5 Flash· LMArena data1,397.5
156Grok 4.1 FastReasoning· LMArena data1,397.2
157Muse Glimmer· LMArena data1,396.4
158OpenAI o32025-04-16· LMArena data1,395.8
159MiniMax-M2.1 Preview· LMArena data1,394.5
160Solar Pro 4· LMArena data1,394.2
161Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,393.8
162MiMo V2 FlashThinking· LMArena data1,389.9
163Qwen3.5 35B A3B· LMArena data1,389.9
164GPT 4.12025-04-14· LMArena data1,386.7
165nova-experimental-chat26-01-10· LMArena data1,384.9
166GLM 4.5 Air· LMArena data1,379.7
167GPT-5 miniHigh· LMArena data1,376.5
168nova-experimental-chat10-20· LMArena data1,376.1
169GLM 4.6v· LMArena data1,375.7
170Nemotron 3 Super 120B A12B· LMArena data1,370.5
171GPT OSS 120B· LMArena data1,369.9
172MiniMax M2.5· LMArena data1,363.4
173Gemma 3 27B IT· LMArena data1,361
174Nova 2 Lite· LMArena data1,356.9
175Granite 4.2 30B· LMArena data1,354.7
176Trinity Large Thinking· LMArena data1,352.1
177MiniMax M1· LMArena data1,352
178Trinity Large Preview· LMArena data1,350.3
179GLM 4.7 Flash· LMArena data1,348
180Command A03-2025· LMArena data1,346.1
181Mercury 2· LMArena data1,345.5
182INTELLECT-3· LMArena data1,344.5
183o4 Mini2025-04-16· LMArena data1,343.1
184Nemotron 3.5 Lightning 30B A3BNVFP4· LMArena data1,342.7
185Nemotron 3 Nano 30B A3BBF16· LMArena data1,335.2
186MiniMax M2· LMArena data1,329.2
187Granite 4.2 8B· LMArena data1,325.1
188Olmo 3.1 32B Instruct· LMArena data1,309.7
189Granite 4.2 3B· LMArena data1,307
190Granite 4.1 8B· LMArena data1,286.4
191Olmo 3 32B Think· LMArena data1,271.9
192Olmo 3.1 32B Think· LMArena data1,245.6

Showing 151–192 of 192 results.

Data credits: LMArena, CC BY 4.0 (licence)