Skip to content

Benchmark

Arena ELO Text Factuality - Industry Entertainment and Sports and Media

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

Models measured
150
Scores recorded
169
Sources
1
IQ weight
2.16

Score distribution

1,414.5
Mean
1,418.2
Median
43.7
Std dev
1,351.5
10th percentile
1,463.3
90th percentile
1,269.3
Min
1,269.31,504.5
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.16 for chat models, measured over 150 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101Qwen3.6 Plus· LMArena data1,409.3
102Grok 4.1· LMArena data1,408.6
103Claude Opus 4.1Thinking 16K, 20250805· LMArena data1,408.5
104DeepSeek-V4-Flash PreviewHigh· LMArena data1,408.5
105Doubao Seed 2.0 Pro· LMArena data1,407.8
106Kimi K2.5Instant· LMArena data1,407
107MiniMax M3· LMArena data1,406.7
108Gemini 2.5 Flash· LMArena data1,406.1
109GPT-5.4 miniHigh· LMArena data1,404.4
110Nemotron 3 UltraNVFP4· LMArena data1,404.2
111Gemini 3.1 Flash Lite· LMArena data1,404.1
112Mistral Large 3· LMArena data1,401.8
113Qwen 3.8 27B· LMArena data1,401.1
114Mistral Medium 3.12508· LMArena data1,400.6
115GPT 5.2High· LMArena data1,400.2
116DeepSeek V3.2Thinking· LMArena data1,400.2
117GPT-6 SolMax· LMArena data1,399.6
118LongCat-Flash-Chat Exp2602· LMArena data1,399.4
119Qwen3 235B A22B Instruct 25072507· LMArena data1,398.6
120Grok 4.3· LMArena data1,398.5
121Claude Haiku 4.520251001· LMArena data1,397.8
122Mistral Medium 3.5· LMArena data1,396.7
123Qwen3 Max Preview· LMArena data1,394.4
124Gemini 2.5 Flash Preview09-2025· LMArena data1,393.4
125NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,391.6
126Grok 40709· LMArena data1,391.4
127Grok 4.1 FastReasoning· LMArena data1,390.3
128GPT-5 Chat· LMArena data1,390
129Inkling 2 Small· LMArena data1,389.7
130MiMo V2 FlashNon-Thinking· LMArena data1,389.4
131Kimi K2 Thinking· LMArena data1,389.4
132MiniMax M2.7· LMArena data1,385.7
133Grok 4 FastReasoning· LMArena data1,384.8
134OpenAI o32025-04-16· LMArena data1,384.5
135MiniMax-M2.1 Preview· LMArena data1,384.1
136Qwen3.5 122B-A10B· LMArena data1,383.7
137nova-experimental-chat11-10· LMArena data1,382.7
138Mistral Large 4· LMArena data1,382.3
139GPT-5.3 Chat· LMArena data1,381.8
140Qwen3.5 27B· LMArena data1,379.7
141Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,378
142GPT 5High· LMArena data1,377.3
143MiMo V2 FlashThinking· LMArena data1,377.1
144Claude Haiku 5.5High· LMArena data1,377
145Inkling Small· LMArena data1,376.7
146Step 3.5 Flash· LMArena data1,376.4
147Qwen3.5 Flash· LMArena data1,374.1
148GPT 5.4 NanoHigh· LMArena data1,369.3
149Qwen3.5 35B A3B· LMArena data1,366.8
150Solar Pro 4· LMArena data1,363.4

Showing 101–150 of 169 results.

Data credits: LMArena, CC BY 4.0 (licence)