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

Gemma 4 31B vs GLM-5.1

GooglevsZ.ai35 shared benchmarks233 head-to-head
BenchmarkGemma 4 31BGLM-5.1
AA Agentic Index14.466
AA Intelligence29.741
AA-LCR68.368
AA-Omniscience-47.90.8
aime_202689.295.8
arena_elo14511468
arena_text_factuality14491458
Artificial Analysis Coding Index43.455.8
coding_arena_elo13641510
critpt1.44.6
gdpval15.549.5
GPQA Diamond85.786.8
HLE26.552.3
HLE (with tools)26.552.3
hmmt_feb_202677.289.4
hmmt_nov_202587.594
IFBench75.676.3
imo_answer_bench74.583.8
itbenchSre37.340.3
MCP Atlas57.275.6
MMLU-Pro85.286
nl2repo15.542.7
OmniScience Accuracy2025.2
OmniScience Non-Hallucination18.170.1
scicode43.443.8
simpleqa_verified9.638.1
SWE-bench Multilingual51.773.3
SWE-bench Pro35.758.4
TauBench V3 - Banking14.813.6
Terminal-Bench 2.042.969
Terminal-Bench 2.143.463.5
Terminal-Bench Hard36.443.2
tool_decathlon21.240.7
τ²-Bench Telecom (AA run)65.597.7
τ³-Bench67.570.6

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.