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 Opus 4.6 vs Qwen3 VL 4B (Reasoning)

AnthropicvsAlibaba25 shared benchmarks241 head-to-head
BenchmarkClaude Opus 4.6Qwen3 VL 4B (Reasoning)
AA Agentic Index67.614.4
AA Intelligence44.97.7
AA-LCR74.323
AA-Omniscience13.7-68.4
AIME 202599.874.5
Artificial Analysis Coding Index48.16.7
critpt12.60
ERQA40.847.3
gdpval55.913.8
GPQA Diamond91.364.1
HLE53.14.6
IFBench62.536.6
LiveCodeBench88.851.3
LiveCodeBench v688.851.3
mathvision71.260
MMLU-Pro89.173.6
MMMU-Pro77.357
OmniScience Accuracy4712.2
OmniScience Non-Hallucination37.28.2
OSWorld-Verified72.731.4
RealWorldQA73.973.2
scicode5217.1
screenspot_pro_no_tools57.749.2
Terminal-Bench Hard65.41.5
τ²-Bench Telecom (AA run)99.315.5

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.