Skip to content

Benchmark

Arena ELO Text Factuality - Industry Software and It Services

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

Models measured
162
Scores recorded
182
Sources
1
IQ weight
2.15

Score distribution

1,476.5
Mean
1,480.3
Median
36.5
Std dev
1,425.2
10th percentile
1,517.7
90th percentile
1,338.8
Min
1,338.81,546.5
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 162 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101Gemma 4 26B A4B· LMArena data1,477.9
102Mistral Large 4· LMArena data1,477.6
103GLM 4.6· LMArena data1,476.4
104DeepSeek V3.2Thinking· LMArena data1,476
105DeepSeek V4 Flash· LMArena data1,475.9
106GPT 5.2· LMArena data1,475.8
107Qwen3.6 Plus· LMArena data1,475.6
108Nemotron 3 UltraNVFP4· LMArena data1,474.5
109Mistral Large 3· LMArena data1,474.1
110GPT 5.1· LMArena data1,473.8
111GPT 5.2High· LMArena data1,473.4
112Inkling Small· LMArena data1,473.1
113DeepSeek V3.2· LMArena data1,473
114Inkling 2 Small· LMArena data1,472.6
115MiniMax M2.7· LMArena data1,471.8
116Gemini 3 FlashMinimal· LMArena data1,471.1
117Claude Haiku 5.5High· LMArena data1,471.1
118GLM 4.7· LMArena data1,471
119GPT-5.5 Instant· LMArena data1,470.7
120Claude Haiku 4.520251001· LMArena data1,470
121DeepSeek V3.2 Exp· LMArena data1,469.7
122DeepSeek-V4-Flash PreviewHigh· LMArena data1,467.9
123NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,467.7
124ERNIE-5.0-Preview1203· LMArena data1,467.1
125Grok 4.7xHigh· LMArena data1,467.1
126MiMo V2 FlashNon-Thinking· LMArena data1,466.6
127Qwen3 235B A22B Instruct 25072507· LMArena data1,466
128Kimi K2 Thinking· LMArena data1,465
129ChatGPT-4o Latest20250326· LMArena data1,465
130Qwen3 Coder· LMArena data1,464.7
131Grok 4.1Thinking· LMArena data1,463.7
132Doubao Seed 2.0 Pro· LMArena data1,462.3
133Qwen3.5 122B-A10B· LMArena data1,460.1
134Step 3.5 Flash· LMArena data1,460
135Gemini 2.5 Flash· LMArena data1,459.8
136Solar Pro 4· LMArena data1,459
137Grok 4.1· LMArena data1,458.9
138Grok 4.3· LMArena data1,458.4
139Mistral Medium 3.12508· LMArena data1,457.7
140nova-experimental-chat26-01-10· LMArena data1,457.3
141Qwen3.5 27B· LMArena data1,456.5
142nova-experimental-chat11-10· LMArena data1,455.6
143GPT 5.4 NanoHigh· LMArena data1,455.1
144Qwen3 Next 80B A3B Instruct· LMArena data1,452.6
145Gemini 3.1 Flash Lite· LMArena data1,451.7
146GPT-5.3 Chat· LMArena data1,448.3
147Qwen3.5 Flash· LMArena data1,447.9
148MiniMax-M2.1 Preview· LMArena data1,447.1
149MiMo V2 FlashThinking· LMArena data1,445.8
150Gemini 2.5 Flash Preview09-2025· LMArena data1,445.3

Showing 101–150 of 182 results.

Data credits: LMArena, CC BY 4.0 (licence)