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 Sonnet 4 vs Qwen3.7 Plus Preview

AnthropicvsAlibaba30 shared benchmarks525 head-to-head
BenchmarkClaude Sonnet 4Qwen3.7 Plus Preview
AA Agentic Index39.220.8
AA Intelligence29.839.4
AA-LCR69.769
AA-Omniscience0.22.4
arena_vision12071263
Artificial Analysis Coding Index37.655.9
critpt1.19.1
gdpval31.222.2
GPQA Diamond7890.3
HLE10.735.6
IFBench5579.1
ifeval87.694.6
LiveCodeBench v648.589.6
mmlu_redux93.694.5
MMLU-Pro8488.5
mmmlu86.589
MMMU-Pro62.480.5
OmniScience Accuracy22.722.5
OmniScience Non-Hallucination70.974.5
OSWorld-Verified42.273.3
scicode4051.3
supergpqa55.771.4
SWE-bench Multilingual56.975.8
SWE-bench Pro42.757.6
SWE-bench Verified80.277.7
TauBench V3 - Banking16.717.9
Terminal-Bench 2.136.361
Terminal-Bench Hard31.147
τ²-Bench Telecom (AA run)64.693
τ³-Bench13.817.9

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.