Skip to content

Benchmark

Arena ELO Text Factuality - Hard Prompts

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

Models measured
168
Scores recorded
192
Sources
1
IQ weight
2.23

Score distribution

1,459.1
Mean
1,464.1
Median
40.8
Std dev
1,401.2
10th percentile
1,502.4
90th percentile
1,311.6
Min
1,311.61,544.8
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.23 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
101Qwen3 Max Preview· LMArena data1,463.2
102GLM 4.6· LMArena data1,463.1
103Claude Opus 4.1Thinking 16K, 20250805· LMArena data1,462.8
104DeepSeek V3.2 ExpThinking· LMArena data1,462.6
105GLM 4.7· LMArena data1,462.5
106DeepSeek V4 Flash· LMArena data1,462.2
107Gemma 4 26B A4B· LMArena data1,461.9
108Grok 4.7xHigh· LMArena data1,460.8
109ERNIE 5.00110· LMArena data1,460.6
110Qwen3.6 Plus· LMArena data1,459.8
111DeepSeek V3.2· LMArena data1,459
112ChatGPT-4o Latest20250326· LMArena data1,458
113MiniMax M3· LMArena data1,457
114DeepSeek V3.2 Exp· LMArena data1,456.8
115DeepSeek V3.2Thinking· LMArena data1,456
116Mistral Medium 3.5· LMArena data1,455.3
117DeepSeek-V4-Flash PreviewHigh· LMArena data1,454.7
118Gemini 2.5 Flash· LMArena data1,454.3
119Nemotron 3 UltraNVFP4· LMArena data1,454
120Qwen3 235B A22B Instruct 25072507· LMArena data1,453.3
121LongCat-Flash-Chat Exp2602· LMArena data1,453.2
122Qwen3 Coder· LMArena data1,453
123Inkling 2 Small· LMArena data1,452.7
124Mistral Large 3· LMArena data1,452.7
125ERNIE-5.0-Preview1203· LMArena data1,451.8
126Claude Haiku 5.5High· LMArena data1,451.4
127Mistral Large 4· LMArena data1,451.2
128MiniMax M2.7· LMArena data1,449.3
129Inkling Small· LMArena data1,448.9
130nova-experimental-chat12-10· LMArena data1,448.4
131Claude Haiku 4.520251001· LMArena data1,447.1
132ERNIE-5.0-Preview1022· LMArena data1,446.9
133Kimi K2 Thinking· LMArena data1,446.8
134NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,446.3
135Grok 4.1· LMArena data1,446.2
136Mistral Medium 3.12508· LMArena data1,445.9
137Grok 4.1Thinking· LMArena data1,445.8
138Qwen3.5 122B-A10B· LMArena data1,444.9
139Qwen3 VL 235B· LMArena data1,444.9
140MiMo V2 FlashNon-Thinking· LMArena data1,444.4
141Qwen3 Next 80B A3B Instruct· LMArena data1,443.7
142Gemini 3.1 Flash Lite· LMArena data1,443.6
143Gemini 2.5 Flash Preview09-2025· LMArena data1,443.6
144Grok 4.3· LMArena data1,443.1
145Doubao Seed 2.0 Pro· LMArena data1,440.9
146MiniMax-M2.1 Preview· LMArena data1,440
147Qwen3.5 27B· LMArena data1,438.4
148GPT-5 Chat· LMArena data1,438.3
149GPT-5.3 Chat· LMArena data1,438.3
150Solar Pro 4· LMArena data1,438

Showing 101–150 of 192 results.

Data credits: LMArena, CC BY 4.0 (licence)