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 5 vs GLM-5.2 Full Open Source

AnthropicvsZ.ai32 shared benchmarks2210 head-to-head
BenchmarkClaude Sonnet 5GLM-5.2 Full Open Source
AA Agentic Index49.745.7
AA Intelligence55.352.6
AA-LCR7776.7
AA-Omniscience16.44.4
arena_elo14631471
arena_text_factuality14531460
Artificial Analysis Coding Index71.568.8
coding_arena_elo15401582
critpt16.920.9
DeepSWE 1.15444
gdpval54.850.3
GDPval-AA v216181514
GPQA Diamond91.191.2
HLE57.454.7
livebench_agentic_coding59.451.8
livebench_coding80.779.7
livebench_data_analysis71.773.7
livebench_instruction_following63.962.3
livebench_language7576.2
livebench_math92.989.8
livebench_reasoning88.778.6
officeqa_pro59.441.4
OmniScience Accuracy4024.3
OmniScience Non-Hallucination60.673.7
scicode53.650.5
simplebench60.658.8
simpleqa_verified2538.1
SWE-bench Pro63.262.1
TauBench V3 - Banking37.334.6
Terminal-Bench 2.180.582.7
toolathlon54.348.2
τ³-Bench28.226.8

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.