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 Qwen3.6 Plus

AnthropicvsAlibaba34 shared benchmarks430 head-to-head
BenchmarkClaude Sonnet 4Qwen3.6 Plus
AA Agentic Index39.229
AA Intelligence29.840.5
AA-LCR69.772.3
AA-Omniscience0.22.6
Artificial Analysis Coding Index37.654.5
critpt1.12.9
frontiermath_tier_408.3
gdpval31.232
GPQA Diamond7890.4
HLE10.728.8
HLE (with tools)20.350.6
HMMT 202515.994.6
IFBench5575.2
ifeval87.694.3
livebench74.870.8
LiveCodeBench v648.587.1
mmlu_redux93.694.5
MMLU-Pro8488.5
mmmlu86.589.5
MMMU74.486
MMMU-Pro62.478.8
OmniScience Accuracy22.726.4
OmniScience Non-Hallucination70.968
OSWorld-Verified42.262.5
scicode4040.7
supergpqa55.771.6
SWE-bench Multilingual56.973.8
SWE-bench Pro42.756.6
SWE-bench Verified80.278.8
TauBench V3 - Banking16.720.8
Terminal-Bench 2.136.361.4
Terminal-Bench Hard31.143.9
τ²-Bench Telecom (AA run)64.697.7
τ³-Bench13.870.7

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.