Skip to content

Benchmark

Arena ELO Text Factuality - Multi Turn

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

Models measured
142
Scores recorded
161
Sources
1
IQ weight
2.11

Score distribution

1,450.4
Mean
1,457.6
Median
36.7
Std dev
1,398.3
10th percentile
1,490.7
90th percentile
1,341.4
Min
1,341.41,524
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.11 for chat models, measured over 142 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101DeepSeek-V4-Flash PreviewHigh· LMArena data1,445.1
102DeepSeek V3.2Thinking· LMArena data1,441.6
103ERNIE 5.00110· LMArena data1,441.2
104DeepSeek V3.2· LMArena data1,440.3
105Mistral Large 3· LMArena data1,439.4
106DeepSeek V3.2 Exp· LMArena data1,438.4
107Grok 4.1Thinking· LMArena data1,438.2
108GLM 4.6· LMArena data1,437.4
109Mistral Large 4· LMArena data1,437.3
110GPT-5.3 Chat· LMArena data1,436.5
111Grok 4.3· LMArena data1,436.4
112Gemini 3.1 Flash Lite· LMArena data1,436.4
113Mistral Medium 3.5· LMArena data1,436.1
114Qwen3.6 Plus· LMArena data1,435.7
115ERNIE-5.0-Preview1203· LMArena data1,433.4
116Kimi K2.5Instant· LMArena data1,433.4
117Gemini 2.5 Flash· LMArena data1,432.8
118Grok 4.1· LMArena data1,432.3
119Claude Haiku 4.520251001· LMArena data1,431.7
120Inkling Small· LMArena data1,430.4
121MiniMax M2.7· LMArena data1,429.9
122GPT 5.4 NanoHigh· LMArena data1,427.2
123GPT 5High· LMArena data1,426.9
124Doubao Seed 2.0 Pro· LMArena data1,426.8
125Grok 4.7xHigh· LMArena data1,426.4
126LongCat-Flash-Chat Exp2602· LMArena data1,425.2
127Qwen3.5 27B· LMArena data1,425.1
128Grok 4 FastReasoning· LMArena data1,424
129Mistral Medium 3.12508· LMArena data1,424
130Kimi K2 Thinking· LMArena data1,422.7
131Qwen3.5 122B-A10B· LMArena data1,421.8
132Gemini 2.5 Flash Preview09-2025· LMArena data1,420.5
133Claude Haiku 5.5High· LMArena data1,420.1
134Qwen3 Next 80B A3B Instruct· LMArena data1,420.1
135MiMo V2 FlashNon-Thinking· LMArena data1,420
136Step 3.5 Flash· LMArena data1,419.6
137MiniMax-M2.1 Preview· LMArena data1,416.4
138Nemotron 3 UltraNVFP4· LMArena data1,415.6
139Qwen3.5 Flash· LMArena data1,415.4
140GPT 4.12025-04-14· LMArena data1,414.2
141Solar Pro 4· LMArena data1,414.2
142Grok 40709· LMArena data1,413.5
143Qwen3.5 35B A3B· LMArena data1,404.2
144OpenAI o32025-04-16· LMArena data1,398.9
145Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,398.3
146Grok 4.1 FastReasoning· LMArena data1,394
147MiMo V2 FlashThinking· LMArena data1,392.8
148MiniMax M2.5· LMArena data1,391.1
149nova-experimental-chat11-10· LMArena data1,388.6
150Nemotron 3 Super 120B A12B· LMArena data1,383.7

Showing 101–150 of 161 results.

Data credits: LMArena, CC BY 4.0 (licence)