Skip to content

Benchmark

Arena ELO Text Factuality - English

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

Models measured
167
Scores recorded
189
Sources
1
IQ weight
2.15

Score distribution

1,448.4
Mean
1,453.2
Median
33.8
Std dev
1,399.6
10th percentile
1,487.4
90th percentile
1,336.9
Min
1,336.91,518.5
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.15 for chat models, measured over 167 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 5High· LMArena data1,423.4
152Qwen3.5 Flash· LMArena data1,423.3
153Grok 40709· LMArena data1,423.1
154Qwen3.5 35B A3B· LMArena data1,420.3
155GPT-5.3 Chat· LMArena data1,419.8
156MiniMax-M2.1 Preview· LMArena data1,419.7
157GPT 4.12025-04-14· LMArena data1,419
158nova-experimental-chat26-01-10· LMArena data1,418.2
159OpenAI o32025-04-16· LMArena data1,413.2
160Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,412.1
161Qwen3 Next 80B A3B Instruct· LMArena data1,411.8
162Nemotron 3 Super 120B A12B· LMArena data1,407.4
163GPT-5 miniHigh· LMArena data1,407.1
164Muse Glimmer· LMArena data1,406.7
165GLM 4.5 Air· LMArena data1,406.6
166GLM 4.6v· LMArena data1,405.3
167Qwen3 VL 235B· LMArena data1,403.6
168MiniMax M2.5· LMArena data1,403.6
169GPT OSS 120B· LMArena data1,401
170Granite 4.2 30B· LMArena data1,399.6
171INTELLECT-3· LMArena data1,398.1
172Nova 2 Lite· LMArena data1,397.5
173Nemotron 3.5 Lightning 30B A3BNVFP4· LMArena data1,395.8
174Nemotron 3 Nano 30B A3BBF16· LMArena data1,391.3
175o4 Mini2025-04-16· LMArena data1,390.3
176Trinity Large Preview· LMArena data1,389.7
177GLM 4.7 Flash· LMArena data1,389.4
178Mercury 2· LMArena data1,388.8
179MiniMax M2· LMArena data1,387.8
180Qwen3 Coder· LMArena data1,387.6
181Trinity Large Thinking· LMArena data1,385.7
182MiniMax M1· LMArena data1,380.7
183Olmo 3.1 32B Instruct· LMArena data1,373.8
184Olmo 3 32B Think· LMArena data1,369.8
185Command A03-2025· LMArena data1,369.7
186Granite 4.2 8B· LMArena data1,364.6
187Olmo 3.1 32B Think· LMArena data1,363.1
188Granite 4.2 3B· LMArena data1,352.2
189Granite 4.1 8B· LMArena data1,336.9

Showing 151–189 of 189 results.

Data credits: LMArena, CC BY 4.0 (licence)