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 26B A4B vs GLM-5.1

GooglevsZ.ai35 shared benchmarks035 head-to-head
BenchmarkGemma 4 26B A4BGLM-5.1
AA Agentic Index32.166
AA Intelligence26.141
AA-LCR61.768
AA-Omniscience-50.80.8
aime_202688.395.8
arena_elo14381468
arena_text_factuality14451458
Artificial Analysis Coding Index39.355.8
browsecomp26.379.3
coding_arena_elo13611510
critpt04.6
gdpval25.749.5
GPQA Diamond82.386.8
HLE19.352.3
HLE (with tools)17.252.3
hmmt_feb_20267989.4
hmmt_nov_202587.594
IFBench72.476.3
imo_answer_bench74.383.8
itbenchSre23.640.3
MCP Atlas5075.6
MMLU-Pro85.286
nl2repo11.642.7
OmniScience Accuracy19.125.2
OmniScience Non-Hallucination13.670.1
scicode40.343.8
SWE-bench Multilingual43.473.3
SWE-bench Pro13.858.4
TauBench V3 - Banking1213.6
Terminal-Bench 2.034.269
Terminal-Bench 2.13963.5
Terminal-Bench Hard2543.2
tool_decathlon1240.7
τ²-Bench Telecom (AA run)43.697.7
τ³-Bench5970.6

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.