VECTOR WIREAI INTELLIGENCE
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models Deals Regulatory Sources

Claude 3.5 Sonnet vs Qwen3 VL 4B (Reasoning)

AnthropicvsAlibaba22 shared benchmarks1111 head-to-head
BenchmarkClaude 3.5 SonnetQwen3 VL 4B (Reasoning)
AA Intelligence107.7
AI2D94.784.9
AIME 20241672.9
AIME 20257.474.5
Artificial Analysis Coding Index30.26.7
BLINK56.565.1
chartqa90.884
GPQA Diamond67.264.1
HLE3.94.6
ifeval90.182.6
LiveCodeBench32.851.3
LiveCodeBench v637.251.3
MathVista67.779.5
mmlu_redux88.986
MMLU-Pro7873.6
MMMU (val) (Pass@1)68.370.8
MMMU-Pro54.757
MMStar62.273.2
OCRBench79081.6
RealWorldQA60.173.2
scicode36.617.1
supergpqa48.246.8

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.