benchgap
Zhipu (GLM) · model

GLM-5V-Turbo benchmark scores

As of 2026-11-22, GLM-5V-Turbo (Zhipu (GLM)) has measured scores on 11 benchmarks and estimated scores on 90 more.

BenchmarkScoreSource
AA-GPQA Diamond80.9%measured
AA-HLE17.1%measured
Artificial Analysis Intelligence Index23.5%measured
CritPt0.6%measured
GDPval-AA17.3%estimated ± 10.5 pp, low confidence
GPQA Diamond79.2%estimated ± 2.4 pp, high confidence
HLE21.5%estimated ± 8.5 pp, medium confidence
IFBench60.8%estimated ± 6.6 pp, medium confidence
AA-LCR70.3%measured
AA-Omniscience Accuracy29.3%measured
BrowseComp66.0%estimated ± 8.8 pp, medium confidence
HLE w/ tools53.5%estimated ± 5.5 pp, medium confidence
IFEval92.3%estimated ± 2.8 pp, high confidence
LongBench v258.7%estimated ± 5.5 pp, medium confidence
VITA-Bench32.2%estimated ± 10.7 pp, low confidence
τ²-bench results98.5%measured
AA-MMMU-Pro72.8%measured
APEX-Agents-AA10.9%estimated ± 9.3 pp, medium confidence
BioMysteryBench (human-difficult)11.6%estimated ± 6.8 pp, low confidence
BFCL v470.6%estimated ± 8.5 pp, low confidence
CyberGym45.7%estimated ± 11.0 pp, low confidence
JobBench17.9%estimated ± 9.3 pp, low confidence
WideResearch65.6%estimated ± 3.3 pp, high confidence
AA Agentic Index13.9%estimated ± 9.4 pp, medium confidence
MMLU-Pro85.3%estimated ± 5.0 pp, medium confidence
AA-IFBench61.1%measured
GPQA82.2%estimated ± 6.1 pp, medium confidence
MMLU90.5%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond80.0%estimated ± 3.2 pp, high confidence
Vals MMLU-Pro84.7%estimated ± 2.9 pp, high confidence
MMMLU85.9%estimated ± 0.7 pp, medium confidence
MMMU82.0%estimated ± 2.7 pp, high confidence
AA MMLU-Pro85.5%estimated ± 0.8 pp, high confidence
Gert Labs23.5%measured
ApprenticeBench3.1%estimated ± 10.4 pp, low confidence
ARC-AGI-175.2%estimated ± 7.8 pp, low confidence
ARC-AGI-231.7%estimated ± 14.4 pp, low confidence
MazeBench0.0%estimated ± 2.7 pp, high confidence
OfficeQA Pro50.3%estimated ± 6.8 pp, low confidence
OSWorld-Verified64.6%estimated ± 3.8 pp, medium confidence
ParseBench-156.7%estimated ± 6.2 pp, medium confidence
CWE-Bench-AA34.6%estimated ± 8.1 pp, low confidence
AA Cyber Index7.5%estimated ± 12.4 pp, low confidence
DeepsecBench-AA6.9%estimated ± 8.2 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)53.0%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)58.3%estimated ± 1.1 pp, low confidence
AA ITBench35.8%estimated ± 4.6 pp, low confidence
Chartography (tools)78.8%estimated ± 4.1 pp, low confidence
CWE-bench v135.2%estimated ± 5.7 pp, low confidence
HLE w/o tools34.7%estimated ± 4.9 pp, high confidence
OSWorld 2.13.0%estimated ± 3.6 pp, medium confidence
Toolathlon-Verified58.2%estimated ± 3.0 pp, high confidence
AA AutomationBench39.7%estimated ± 9.9 pp, low confidence
GDP.pdf11.0%estimated ± 4.2 pp, medium confidence
ARC-AGI-31.3%estimated ± 9.8 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
CWE-bench28.4%estimated ± 6.2 pp, low confidence
MKA32.8%estimated ± 4.6 pp, medium confidence
Hermes Index16.5%estimated ± 5.7 pp, low confidence
ParseBench-261.6%estimated ± 6.2 pp, medium confidence
CharXiv79.5%estimated ± 6.3 pp, low confidence
CharXiv w/o tools78.8%estimated ± 2.5 pp, medium confidence
ExploitGym0.0%estimated ± 8.3 pp, low confidence
AI2D_TEST88.9%estimated ± 2.0 pp, medium confidence
C-Eval92.6%estimated ± 1.0 pp, medium confidence
Claw-Eval53.8%measured
CountBench93.5%estimated ± 2.9 pp, medium confidence
DynaMath84.0%estimated ± 3.0 pp, medium confidence
ERQA53.4%estimated ± 3.1 pp, high confidence
MathVision82.3%estimated ± 3.1 pp, high confidence
MCP Atlas40.9%estimated ± 13.5 pp, low confidence
MCP-Tasks62.4%estimated ± 6.4 pp, low confidence
MMLU-Redux94.7%estimated ± 0.8 pp, medium confidence
MMMU-Pro74.1%estimated ± 1.5 pp, high confidence
RealWorldQA81.6%estimated ± 2.9 pp, medium confidence
ScreenSpot Pro73.1%estimated ± 10.8 pp, low confidence
SuperGPQA67.9%estimated ± 9.3 pp, medium confidence
Toolathlon37.8%estimated ± 8.0 pp, medium confidence
V*94.6%estimated ± 7.5 pp, medium confidence
Video-MME (w/o subtitle)81.5%estimated ± 1.7 pp, medium confidence
Video-MME (with subtitle)83.6%estimated ± 3.7 pp, medium confidence
HealthBench Hard6.5%estimated ± 8.6 pp, low confidence
MedXpertQA (MM)65.7%estimated ± 6.5 pp, low confidence
MMLU-Pro (Arcee)79.4%estimated ± 4.0 pp, medium confidence
ResearchClawBench14.8%estimated ± 1.3 pp, high confidence
Finance Agent v255.1%estimated ± 2.4 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
HealthBench (raw)24.2%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)44.9%estimated ± 3.4 pp, low confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
HealthBench Professional (raw)36.5%estimated ± 4.5 pp, medium confidence
HLE-Verified23.8%estimated ± 7.1 pp, low confidence
STEMBench2.4%estimated ± 0.2 pp, medium confidence
SimpleQA30.9%estimated ± 4.3 pp, medium confidence
Agents' Last Exam29.6%estimated ± 9.7 pp, low confidence
BabyVision w/ Python86.2%estimated ± 4.0 pp, low confidence
MRCRv275.3%estimated ± 11.3 pp, low confidence
MMLongBench-Doc60.9%estimated ± 2.6 pp, low confidence
BioBasicsBench34.1%estimated ± 3.8 pp, low confidence
LifeVal1.7%estimated ± 5.0 pp, low confidence
MMMU-Pro w/ Python76.2%estimated ± 2.0 pp, high confidence