Skip to content

Benchmark

Arena ELO Text Factuality

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

Models measured
170
Scores recorded
194
Sources
1
IQ weight
2.26

Score distribution

1,435.9
Mean
1,441.9
Median
39.3
Std dev
1,379.4
10th percentile
1,478.9
90th percentile
1,299.6
Min
1,299.61,522.2
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.26 for chat models, measured over 170 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
151Step 3.5 Flash· LMArena data1,416
152Solar Pro 4· LMArena data1,414.6
153nova-experimental-chat11-10· LMArena data1,414.6
154Qwen3 VL 235B· LMArena data1,414.6
155Qwen3.5 Flash· LMArena data1,413.7
156Grok 4.1 FastReasoning· LMArena data1,413.7
157MiniMax-M2.1 Preview· LMArena data1,410.5
158MiMo V2 FlashThinking· LMArena data1,409.3
159GPT 4.12025-04-14· LMArena data1,407.6
160Qwen3.5 35B A3B· LMArena data1,407.3
161Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,406.4
162OpenAI o32025-04-16· LMArena data1,404.5
163Muse Glimmer· LMArena data1,402.3
164Kimi K2 Preview0905· LMArena data1,401.9
165nova-experimental-chat26-01-10· LMArena data1,401.5
166Qwen3 Coder· LMArena data1,399.9
167nova-experimental-chat10-20· LMArena data1,399.6
168GPT-5 miniHigh· LMArena data1,394.2
169GLM 4.5 Air· LMArena data1,394.1
170GLM 4.6v· LMArena data1,391.2
171Nemotron 3 Super 120B A12B· LMArena data1,389.5
172MiniMax M2.5· LMArena data1,384.9
173GPT OSS 120B· LMArena data1,384.5
174Nova 2 Lite· LMArena data1,379.5
175Gemma 3 27B IT· LMArena data1,379.4
176Granite 4.2 30B· LMArena data1,375.4
177INTELLECT-3· LMArena data1,372.8
178Trinity Large Preview· LMArena data1,371.7
179Trinity Large Thinking· LMArena data1,369.9
180MiniMax M1· LMArena data1,369.6
181GLM 4.7 Flash· LMArena data1,369.5
182Nemotron 3.5 Lightning 30B A3BNVFP4· LMArena data1,368.8
183o4 Mini2025-04-16· LMArena data1,367.5
184Mercury 2· LMArena data1,367.5
185Command A03-2025· LMArena data1,362.8
186Nemotron 3 Nano 30B A3BBF16· LMArena data1,362.2
187MiniMax M2· LMArena data1,359.8
188Granite 4.2 8B· LMArena data1,341.4
189Olmo 3.1 32B Instruct· LMArena data1,341.3
190Granite 4.2 3B· LMArena data1,323.5
191Olmo 3 32B Think· LMArena data1,318.4
192Granite 4.1 8B· LMArena data1,310.9
193Mercury· LMArena data1,304
194Olmo 3.1 32B Think· LMArena data1,299.6

Showing 151–194 of 194 results.

Data credits: LMArena, CC BY 4.0 (licence)