benchgap
Zhipu (GLM) · model

GLM-4.6 benchmark scores

As of 2026-11-22, GLM-4.6 (Zhipu (GLM)) has measured scores on 12 benchmarks and estimated scores on 57 more.

BenchmarkScoreSource
AA-GPQA Diamond63.2%measured
AA-HLE5.5%measured
AA-SciCode45.7%estimated ± 3.8 pp, high confidence
Artificial Analysis Intelligence Index14.9%measured
CritPt0.0%measured
GDPval-AA10.9%estimated ± 11.0 pp, low confidence
GPQA Diamond81.6%estimated ± 1.8 pp, medium confidence
HLE17.0%estimated ± 8.5 pp, medium confidence
IFBench53.9%estimated ± 6.6 pp, low confidence
AA-LCR26.3%measured
LiveCodeBench v686.9%estimated ± 2.2 pp, medium confidence
AA-Omniscience Accuracy21.4%measured
SciCode38.8%estimated ± 2.9 pp, low confidence
BrowseComp65.4%estimated ± 13.0 pp, low confidence
HLE w/ tools27.8%estimated ± 5.5 pp, low confidence
IFEval87.7%estimated ± 2.8 pp, high confidence
LongBench v251.2%estimated ± 5.5 pp, low confidence
τ²-bench results76.9%measured
AA Coding Index41.1%estimated ± 6.9 pp, medium confidence
APEX-Agents-AA1.6%estimated ± 11.4 pp, low confidence
BioMysteryBench (human-difficult)0.0%estimated ± 6.8 pp, low confidence
SWE-bench Verified71.5%estimated ± 4.5 pp, high confidence
BFCL v459.7%estimated ± 8.5 pp, low confidence
SWE-bench Pro53.2%estimated ± 2.9 pp, low confidence
AA Agentic Index18.3%estimated ± 12.7 pp, low confidence
MMLU-Pro83.2%estimated ± 4.8 pp, high confidence
AA-IFBench36.7%measured
GPQA77.2%estimated ± 4.5 pp, high confidence
MMLU89.7%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond74.5%measured
Vals LiveCodeBench81.0%measured
Vals MMLU-Pro82.2%measured
MMMLU83.3%estimated ± 0.7 pp, medium confidence
AA MMLU-Pro84.6%estimated ± 0.7 pp, medium confidence
ARC-AGI-154.9%estimated ± 6.5 pp, low confidence
ARC-AGI-20.0%estimated ± 13.8 pp, low confidence
CursorBench 3.259.1%estimated ± 7.2 pp, low confidence
FrontierCode 1.1 Main32.7%estimated ± 6.2 pp, low confidence
Vals SWE-bench59.6%estimated ± 7.1 pp, medium confidence
VulcanBench v381.4%estimated ± 5.6 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)50.3%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)49.8%estimated ± 1.1 pp, low confidence
CursorBench 4.037.9%estimated ± 4.5 pp, high confidence
HLE w/o tools25.8%estimated ± 4.9 pp, high confidence
PostTrainBench v1.119.9%estimated ± 10.5 pp, low confidence
ARC-AGI-30.0%estimated ± 8.6 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
Vibe Code Bench3.1%measured
C-Eval90.0%estimated ± 1.0 pp, medium confidence
MMLU-Redux93.7%estimated ± 0.8 pp, medium confidence
NL2Repo45.7%estimated ± 7.9 pp, low confidence
PostTrainBench v119.0%estimated ± 3.1 pp, low confidence
SuperGPQA64.9%estimated ± 9.3 pp, medium confidence
AA LiveCodeBench83.1%estimated ± 3.4 pp, low confidence
HealthBench Hard0.0%estimated ± 8.6 pp, low confidence
MMLU-Pro (Arcee)77.1%estimated ± 4.0 pp, low confidence
React Native Evals27.9%estimated ± 3.0 pp, low confidence
SWE-Rebench0.0%estimated ± 6.5 pp, low confidence
PostTrainBench17.0%estimated ± 8.3 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
HealthBench (length-adjusted)54.1%estimated ± 3.7 pp, medium confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
HLE-Verified16.6%estimated ± 7.1 pp, low confidence
LABBench278.7%estimated ± 1.8 pp, low confidence
STEMBench2.3%estimated ± 0.2 pp, low confidence
SimpleQA20.0%estimated ± 4.3 pp, medium confidence
MRCRv222.8%estimated ± 11.3 pp, low confidence
MMLongBench-Doc55.2%estimated ± 2.6 pp, low confidence
BioBasicsBench34.1%estimated ± 3.8 pp, low confidence