Skip to content

Benchmark

Arena ELO - Industry Business and Management and Financial Operations

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

Models measured
359
Scores recorded
416
Sources
1
IQ weight
1.28

Score distribution

1,295.6
Mean
1,344.1
Median
158.7
Std dev
1,054.4
10th percentile
1,457
90th percentile
734.2
Min
734.21,520.2
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.28 for chat models, measured over 359 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101Grok 4.20 Multi-Agent0309, beta· LMArena data1,423.2
102ERNIE-5.0-Preview1203· LMArena data1,423.2
103Gemini 3 FlashMinimal· LMArena data1,422.8
104Gemini 3.5 Flash Lite· LMArena data1,422.7
105Qwen3 Next 80B A3B Instruct· LMArena data1,422
106GPT 5.1· LMArena data1,420.2
107GLM 4.5· LMArena data1,420
108Mistral Large 3· LMArena data1,418.4
109Qwen3 235B A22B Instruct 25072507· LMArena data1,418
110GPT-5.4 miniHigh· LMArena data1,417.7
111Mistral Medium 3.12508· LMArena data1,417.6
112nova-experimental-chat11-10· LMArena data1,417.1
113ERNIE-5.0-Preview1022· LMArena data1,417
114GLM 4.6· LMArena data1,416.5
115Grok 4.1Thinking· LMArena data1,416
116Inkling 2 Small· LMArena data1,415.6
117Qwen3.5 122B-A10B· LMArena data1,414.3
118DeepSeek V3.1 TerminusThinking· LMArena data1,414.1
119Grok 4.6High· LMArena data1,414.1
120Hunyuan Vision 1.5 Thinking· LMArena data1,414.1
121GPT 5.2High· LMArena data1,414
122LongCat-Flash-Chat Exp2602· LMArena data1,413.4
123Inkling Small· LMArena data1,413.1
124GPT-6.2 AstraMax· LMArena data1,412.9
125DeepSeek V3.2 Exp· LMArena data1,412.7
126Qwen 3 235B A22B2507, thinking· LMArena data1,412.5
127GPT-6.1 TerraMax· LMArena data1,411.7
128DeepSeek-V4-Flash PreviewHigh· LMArena data1,410.5
129Grok 3 Preview02-24· LMArena data1,410
130DeepSeek V3.2· LMArena data1,409.6
131GPT-5.5 Instant· LMArena data1,409.6
132GPT 5.2· LMArena data1,409.3
133DeepSeek V3.1Thinking· LMArena data1,409.3
134DeepSeek V3.2Thinking· LMArena data1,409.1
135MiniMax M2.7· LMArena data1,406.7
136Claude Opus 4.120250805· LMArena data1,405.7
137Kimi K2.5Instant· LMArena data1,405.4
138Muse Glimmer· LMArena data1,405.1
139DeepSeek V3.1· LMArena data1,405
140Claude Opus 4.1Thinking 16K, 20250805· LMArena data1,404.9
141Gemini 2.5 Flash· LMArena data1,403.4
142MiMo V2 FlashNon-Thinking· LMArena data1,402.4
143DeepSeek R10528· LMArena data1,401.3
144nova-experimental-chat10-20· LMArena data1,400.5
145GPT-5 Chat· LMArena data1,399.5
146Claude Haiku 4.520251001· LMArena data1,399.4
147Qwen3.5 27B· LMArena data1,398.3
148NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,398.2
149Gemini 2.5 Flash Preview09-2025· LMArena data1,397.9
150Kimi K2 Thinking· LMArena data1,397.5

Showing 101–150 of 416 results.

Data credits: LMArena, CC BY 4.0 (licence)