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 GLM-5.2 Full Open Source

AnthropicvsZ.ai24 shared benchmarks024 head-to-head
BenchmarkClaude Sonnet 4GLM-5.2 Full Open Source
AA Agentic Index39.245.7
AA Intelligence29.852.6
AA-LCR69.776.7
AA-Omniscience0.24.4
arc_agi_163.777
ARC-AGI-213.622.8
Artificial Analysis Coding Index37.668.8
critpt1.120.9
gdpval31.250.3
GPQA Diamond7891.2
HLE10.754.7
HLE (with tools)20.354.7
HMMT 202515.994.4
IFBench5573.3
OmniScience Accuracy22.724.3
OmniScience Non-Hallucination70.973.7
scicode4050.5
simplebench45.558.8
SWE-bench Pro42.762.1
TauBench V3 - Banking16.734.6
Terminal-Bench 2.136.382.7
Terminal-Bench Hard31.150.8
τ²-Bench Telecom (AA run)64.699.1
τ³-Bench13.826.8

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.