Neura Intelligence Index

AI Model Benchmarks

Back to Leaderboard

Claude 3 Sonnet vs DeepSeek VL2 Small

Claude 3 Sonnet

Anthropic 🇺🇸

8.2

#347—

DeepSeek VL2 Small

DeepSeek 🇨🇳

7.8

#350—

Category Comparison

Benchmark-by-Benchmark

reasoning

Benchmark	Claude 3 Sonnet	DeepSeek VL2 Small
GPQA Diamond	40.4	—

multimodal

Benchmark	Claude 3 Sonnet	DeepSeek VL2 Small
MMMU	—	48

Category Winners

reasoning

Claude 3 Sonnet

8.2

multimodal

DeepSeek VL2 Small

7.8

Claude 3 Sonnet vs DeepSeek VL2 Small — Benchmark Comparison | Neura Market