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

Gemini 3 Pro vs GLM-5.1

GooglevsZ.ai39 shared benchmarks1524 head-to-head
BenchmarkGemini 3 ProGLM-5.1
AA Agentic Index5266
AA Intelligence40.641
AA-LCR7368
AA-Omniscience15.30.8
aime_202691.795.8
arena_elo14851468
arena_text_factuality14811458
Artificial Analysis Coding Index46.555.8
browsecomp59.279.3
browsecomp_with_context_manager59.279.3
coding_arena_elo14381510
critpt9.14.6
cybergym39.968.7
frontiermath_tier_418.812.5
gdpval34.249.5
GDPval-AA (Elo)11951535
GPQA Diamond91.986.8
HLE45.852.3
HLE (with tools)45.852.3
hmmt_feb_202686.489.4
hmmt_nov_202593.394
IFBench70.476.3
imo_answer_bench83.383.8
livebench73.470.2
MCP Atlas70.375.6
MMLU-Pro90.186
OmniScience Accuracy55.825.2
OmniScience Non-Hallucination1070.1
scicode56.143.8
simplebench76.455.1
simpleqa_verified72.938.1
SWE-bench Multilingual68.773.3
SWE-bench Pro43.358.4
Terminal-Bench 2.054.269
Terminal-Bench Hard56.943.2
tool_decathlon36.440.7
toolathlon36.440.7
Vending-Bench 2547816563441
τ²-Bench Telecom (AA run)9897.7

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.