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 4.5 vs GLM-5.2 Full Open Source

AnthropicvsZ.ai32 shared benchmarks230 head-to-head
BenchmarkClaude Sonnet 4.5GLM-5.2 Full Open Source
AA Agentic Index50.645.7
AA Intelligence37.452.6
AA-LCR68.376.7
AA-Omniscience-0.14.4
arc_agi_163.777
ARC-AGI-213.622.8
arena_elo14561471
arena_text_factuality14481460
Artificial Analysis Coding Index52.168.8
coding_arena_elo13921582
critpt1.120.9
gdpval40.450.3
GPQA Diamond83.491.2
HLE19.854.7
HLE (with tools)3254.7
HMMT 202574.694.4
hmmt_nov_202581.794.4
IFBench57.373.3
imo_answer_bench65.991
MCP Atlas59.582.6
OmniScience Accuracy32.924.3
OmniScience Non-Hallucination50.973.7
scicode4550.5
simplebench54.358.8
simpleqa_verified23.638.1
SWE-bench Pro43.662.1
TauBench V3 - Banking24.534.6
Terminal-Bench 2.155.882.7
Terminal-Bench Hard35.650.8
toolathlon4148.2
τ²-Bench Telecom (AA run)78.199.1
τ³-Bench1926.8

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.