benchgap
Zhipu (GLM) · model

GLM-4.7 benchmark scores

As of 2026-11-21, GLM-4.7 (Zhipu (GLM)) has measured scores on 31 benchmarks and estimated scores on 112 more.

BenchmarkScoreSource
AA-GPQA Diamond85.9%measured
AA-HLE27.4%measured
AA-SciCode42.7%estimated ± 3.4 pp, high confidence
AIME2695.6%estimated ± 1.0 pp, medium confidence
Artificial Analysis Intelligence Index22.2%measured
CritPt1.7%measured
GDPval-AA25.7%measured
GPQA Diamond85.7%estimated ± 0.1 pp, medium confidence
HLE24.8%measured
IFBench66.0%estimated ± 6.6 pp, medium confidence
AA-LCR71.0%measured
LiveCodeBench v684.9%measured
AA-Omniscience Accuracy29.3%measured
SciCode41.1%estimated ± 2.9 pp, low confidence
BrowseComp52.0%measured
HLE w/ tools46.2%estimated ± 5.3 pp, low confidence
IFEval92.7%estimated ± 2.8 pp, high confidence
LongBench v259.1%estimated ± 5.5 pp, medium confidence
VITA-Bench15.5%measured
τ²-bench results95.9%measured
AA Coding Index45.3%measured
APEX-Agents18.6%estimated ± 9.4 pp, low confidence
APEX-Agents-AA8.5%estimated ± 4.4 pp, medium confidence
BioMysteryBench (human-difficult)23.5%estimated ± 6.8 pp, low confidence
DeepSearchQA75.4%estimated ± 6.8 pp, low confidence
SWE-bench Verified73.8%measured
BFCL v473.6%estimated ± 2.7 pp, high confidence
CyberGym53.5%estimated ± 6.0 pp, medium confidence
JobBench23.1%estimated ± 8.7 pp, medium confidence
SkillsBench27.0%estimated ± 4.1 pp, low confidence
SWE-bench Pro51.6%estimated ± 4.5 pp, high confidence
WideResearch61.6%estimated ± 3.5 pp, medium confidence
AA Agentic Index19.8%estimated ± 3.1 pp, high confidence
MMLU-Pro84.3%measured
AA-IFBench67.9%measured
AIME 202494.8%estimated ± 2.6 pp, high confidence
BBH98.4%estimated ± 2.8 pp, medium confidence
FailureSensorIQ66.2%estimated ± 1.8 pp, medium confidence
GPQA85.7%measured
MMLU90.5%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond80.1%measured
Vals LiveCodeBench82.2%measured
Vals MMLU-Pro82.7%measured
MATH-50098.9%estimated ± 2.0 pp, high confidence
MMMLU87.0%estimated ± 0.7 pp, medium confidence
Chess Puzzles21.0%measured
AIME 202595.7%measured
AA MMLU-Pro85.6%measured
Gert Labs40.0%measured
AA Harvey LAB v1.083.3%estimated ± 9.8 pp, low confidence
AA Tau3 Banking30.5%estimated ± 4.1 pp, high confidence
ARC-AGI-167.9%estimated ± 6.5 pp, medium confidence
ARC-AGI-225.8%estimated ± 10.9 pp, low confidence
CursorBench 3.143.3%estimated ± 5.8 pp, low confidence
CursorBench 3.230.5%estimated ± 4.4 pp, medium confidence
EBR-bench10.0%estimated ± 12.7 pp, low confidence
FrontierCode 1.1 Main16.5%estimated ± 4.2 pp, low confidence
FrontierSWE v26.2%estimated ± 9.5 pp, low confidence
Furniture Assembly27.2%estimated ± 14.1 pp, low confidence
MaxxBench41.0%estimated ± 10.3 pp, low confidence
MazeBench0.4%estimated ± 5.5 pp, low confidence
Mystery Game Puzzles15.1%estimated ± 2.2 pp, low confidence
NYT Connections63.8%estimated ± 12.6 pp, low confidence
OSWorld-Verified55.8%estimated ± 5.5 pp, medium confidence
Terminal-Bench Hard41.5%estimated ± 4.0 pp, medium confidence
Vals SWE-bench69.4%measured
Terminal-Bench 2.1 (Vals AI)35.5%estimated ± 6.4 pp, medium confidence
VulcanBench v382.0%estimated ± 5.6 pp, low confidence
CWE-Bench-AA36.1%estimated ± 6.4 pp, medium confidence
AA Cyber Index26.8%estimated ± 13.5 pp, low confidence
DeepsecBench-AA1.5%estimated ± 8.9 pp, low confidence
HealthBench Professional (length-adjusted, Artificial Analysis)52.6%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)57.3%estimated ± 1.1 pp, low confidence
AA ITBench36.4%estimated ± 2.8 pp, high confidence
CursorBench 4.030.8%estimated ± 3.4 pp, medium confidence
CWE-bench v135.2%estimated ± 6.4 pp, low confidence
DeepSWE56.3%estimated ± 7.2 pp, low confidence
DRACO73.1%estimated ± 2.0 pp, medium confidence
FrontierPhysics0.0%estimated ± 6.1 pp, low confidence
HLE w/o tools26.3%estimated ± 4.9 pp, high confidence
OSWorld 2.1 Offline2.8%estimated ± 1.9 pp, low confidence
PostTrainBench v1.114.8%estimated ± 3.7 pp, medium confidence
SpireClimb0.0%estimated ± 10.3 pp, low confidence
StealthMark37.5%estimated ± 9.7 pp, low confidence
Toolathlon-Verified51.9%estimated ± 3.1 pp, medium confidence
GDP.pdf17.0%estimated ± 4.6 pp, medium confidence
ARC-AGI-30.0%estimated ± 8.6 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
MKA21.7%estimated ± 6.4 pp, low confidence
SkillsBench official leaderboard (BenchFlow)49.4%estimated ± 6.2 pp, medium confidence
BinaryAudit24.6%measured
OTelBench13.0%measured
Vibe Code Bench20.6%estimated ± 6.6 pp, low confidence
FACTS Multimodal36.6%estimated ± 5.6 pp, medium confidence
Hermes Bench56.4%estimated ± 2.9 pp, high confidence
Hermes Index23.5%estimated ± 8.7 pp, medium confidence
ExploitBench21.4%estimated ± 13.4 pp, low confidence
ExploitGym1.1%estimated ± 10.6 pp, low confidence
C-Eval91.6%estimated ± 0.9 pp, medium confidence
Claw-Eval62.7%estimated ± 6.4 pp, low confidence
DeepPlanning26.2%estimated ± 9.1 pp, low confidence
HMMT Feb 202597.1%measured
HMMT Feb 202687.4%estimated ± 1.2 pp, medium confidence
HMMT Nov 202594.9%estimated ± 1.5 pp, high confidence
MCP Atlas48.8%estimated ± 10.3 pp, low confidence
MMAnswerBench82.9%estimated ± 2.0 pp, low confidence
MMLU-Redux92.8%estimated ± 0.6 pp, high confidence
NL2Repo36.1%estimated ± 3.4 pp, high confidence
PostTrainBench v111.2%estimated ± 3.6 pp, medium confidence
QwenClawBench52.0%estimated ± 2.0 pp, low confidence
SuperGPQA65.6%estimated ± 7.2 pp, medium confidence
Terminal-Bench 2.041.0%measured
Toolathlon26.1%estimated ± 4.2 pp, medium confidence
AA LiveCodeBench89.4%measured
HealthBench Hard13.9%estimated ± 8.6 pp, low confidence
MMLU-Pro (Arcee)83.5%estimated ± 4.0 pp, medium confidence
React Native Evals76.9%estimated ± 2.7 pp, medium confidence
ResearchClawBench16.0%estimated ± 2.2 pp, medium confidence
SWE-Rebench58.7%measured
PostTrainBench12.4%estimated ± 3.7 pp, medium confidence
DAYJOB0.4%estimated ± 6.3 pp, medium confidence
DAYJOB Healthcare0.1%estimated ± 6.1 pp, low confidence
BioMysteryBench (human-solvable)81.7%estimated ± 0.6 pp, low confidence
HealthBench (raw)36.1%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)48.8%estimated ± 3.4 pp, low confidence
HealthBench Professional56.7%estimated ± 4.2 pp, low confidence
HealthBench Professional (raw)47.5%estimated ± 4.5 pp, medium confidence
HLE-Verified23.8%estimated ± 7.1 pp, low confidence
LABBench279.0%estimated ± 1.8 pp, low confidence
ScarfBench24.4%estimated ± 9.1 pp, low confidence
BlenderWorld (text-only)70.6%estimated ± 4.0 pp, medium confidence
Cookie-Bench77.3%estimated ± 2.5 pp, medium confidence
STEMBench2.4%estimated ± 0.2 pp, medium confidence
SimpleQA30.9%estimated ± 4.3 pp, medium confidence
LiveCodeBench75.4%estimated ± 14.6 pp, low confidence
OpenHarmony Bench v1.045.3%estimated ± 2.8 pp, medium confidence
SEC-Bench Pro31.8%estimated ± 12.3 pp, low confidence
MRCRv277.6%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.0%estimated ± 2.6 pp, low confidence
BioBasicsBench33.9%estimated ± 2.8 pp, low confidence
LifeVal20.7%estimated ± 1.6 pp, low confidence
ExploitBench Internal Port0.0%estimated ± 1.4 pp, low confidence
PinchBench88.0%estimated ± 3.6 pp, medium confidence