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-5.1

AnthropicvsZ.ai35 shared benchmarks629 head-to-head
BenchmarkClaude Sonnet 4.5GLM-5.1
AA Agentic Index50.666
AA Intelligence37.441
AA-LCR68.368
AA-Omniscience-0.10.8
arena_elo14561468
arena_text_factuality14481458
Artificial Analysis Coding Index52.155.8
browsecomp24.179.3
coding_arena_elo13921510
critpt1.14.6
frontiermath_tier_44.212.5
gdpval40.449.5
GPQA Diamond83.486.8
HLE19.852.3
HLE (with tools)3252.3
HMMT 202574.694
hmmt_nov_202581.794
IFBench57.376.3
imo_answer_bench65.983.8
MCP Atlas59.575.6
MMLU-Pro88.286
OmniScience Accuracy32.925.2
OmniScience Non-Hallucination50.970.1
scicode4543.8
simplebench54.355.1
simpleqa_verified23.638.1
SWE-bench Multilingual6873.3
SWE-bench Pro43.658.4
TauBench V3 - Banking24.513.6
Terminal-Bench 2.05069
Terminal-Bench 2.155.863.5
Terminal-Bench Hard35.643.2
toolathlon4140.7
τ²-Bench Telecom (AA run)78.197.7
τ³-Bench1970.6

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.