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
101Qwen 3.8 27B· LMArena data1,449.9
102Claude Opus 4.1Thinking 16K, 20250805· LMArena data1,449.6
103GPT 5.2High· LMArena data1,449.2
104DeepSeek V3.2Thinking· LMArena data1,448.9
105GPT-5.4 miniHigh· LMArena data1,448.9
106Mistral Large 3· LMArena data1,448.6
107GPT 5.1· LMArena data1,448.4
108DeepSeek V4 Flash· LMArena data1,448.3
109MiniMax M3· LMArena data1,447.4
110ERNIE-5.0-Preview1203· LMArena data1,445.8
111Kimi K2.5Instant· LMArena data1,445.7
112NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,445.6
113Mistral Medium 3.5· LMArena data1,445.5
114Claude Opus 4.120250805· LMArena data1,445.3
115Nemotron 3 UltraNVFP4· LMArena data1,445.2
116GPT 5.2· LMArena data1,445.2
117GPT-5.5 Instant· LMArena data1,444.9
118Mistral Medium 3.12508· LMArena data1,444.5
119Grok 4.7xHigh· LMArena data1,444.4
120DeepSeek-V4-Flash PreviewHigh· LMArena data1,444.3
121Grok 4.1Thinking· LMArena data1,442.9
122ERNIE-5.0-Preview1022· LMArena data1,442.4
123nova-experimental-chat12-10· LMArena data1,441.9
124Grok 4.1· LMArena data1,441.1
125Inkling 2 Small· LMArena data1,440.8
126MiMo V2 FlashNon-Thinking· LMArena data1,440.5
127Gemini 2.5 Flash· LMArena data1,440.4
128GPT-6 SolMax· LMArena data1,440.2
129MiniMax M2.7· LMArena data1,440
130Qwen3.5 122B-A10B· LMArena data1,438.6
131Qwen3 235B A22B Instruct 25072507· LMArena data1,438
132Kimi K2 Thinking· LMArena data1,437.2
133Qwen3.5 27B· LMArena data1,435.9
134Grok 4.3· LMArena data1,435.3
135Claude Haiku 4.520251001· LMArena data1,434.7
136Solar Pro 4· LMArena data1,433.8
137Mistral Large 4· LMArena data1,433.5
138Gemini 3.1 Flash Lite· LMArena data1,433.5
139Inkling Small· LMArena data1,433.1
140Step 3.5 Flash· LMArena data1,432.2
141Claude Haiku 5.5High· LMArena data1,430.3
142Gemini 2.5 Flash Preview09-2025· LMArena data1,429.1
143Doubao Seed 2.0 Pro· LMArena data1,429
144Grok 4 FastReasoning· LMArena data1,428.5
145GPT-5 Chat· LMArena data1,427.2
146Grok 4.1 FastReasoning· LMArena data1,425.4
147nova-experimental-chat11-10· LMArena data1,425.3
148GPT 5.4 NanoHigh· LMArena data1,424.8
149nova-experimental-chat10-20· LMArena data1,424.7
150MiMo V2 FlashThinking· LMArena data1,424.1

Showing 101–150 of 189 results.

Data credits: LMArena, CC BY 4.0 (licence)