benchgap
Zhipu (GLM) · model

GLM-5.1 benchmark scores

As of 2026-11-22, GLM-5.1 (Zhipu (GLM)) has measured scores on 42 benchmarks and estimated scores on 124 more.

BenchmarkScoreSource
AA-GPQA Diamond86.8%measured
AA-HLE30.1%measured
AA-SciCode44.8%measured
AIME2695.3%measured
Artificial Analysis Intelligence Index26.1%measured
CritPt4.6%measured
GDPval-AA30.8%measured
GPQA Diamond86.2%measured
HLE31.0%measured
IFBench74.6%estimated ± 6.6 pp, medium confidence
AA-LCR73.7%measured
LiveCodeBench v688.7%estimated ± 1.7 pp, high confidence
AA-Omniscience Accuracy23.7%measured
SciCode39.5%estimated ± 2.9 pp, low confidence
Terminal-Bench 2.174.3%estimated ± 6.7 pp, medium confidence
BrowseComp68.0%measured
HLE w/ tools52.3%measured
IFEval93.1%estimated ± 2.8 pp, high confidence
LongBench v260.8%estimated ± 5.5 pp, medium confidence
VITA-Bench38.9%estimated ± 6.7 pp, low confidence
τ²-bench results97.7%measured
AA Coding Index55.8%measured
APEX-Agents23.1%estimated ± 9.4 pp, low confidence
APEX-Agents-AA15.1%estimated ± 4.4 pp, high confidence
BioMysteryBench (human-difficult)36.2%estimated ± 6.8 pp, low confidence
DeepSearchQA87.2%estimated ± 4.5 pp, high confidence
SWE-bench Verified79.5%estimated ± 2.3 pp, high confidence
AutomationBench48.6%estimated ± 9.1 pp, low confidence
BFCL v474.5%estimated ± 2.7 pp, high confidence
CyberGym68.7%measured
JobBench44.1%estimated ± 7.9 pp, medium confidence
SkillsBench39.7%estimated ± 4.1 pp, low confidence
SWE-bench Pro58.4%measured
τ³-bench results70.6%measured
WideResearch82.1%estimated ± 1.6 pp, medium confidence
AA Agentic Index25.2%measured
MMLU-Pro86.0%estimated ± 4.8 pp, high confidence
AA-IFBench76.3%measured
FailureSensorIQ67.1%estimated ± 1.7 pp, high confidence
GPQA86.1%estimated ± 1.2 pp, high confidence
MMLU90.4%estimated ± 0.9 pp, high confidence
Vals GPQA Diamond84.5%measured
Vals LiveCodeBench81.4%measured
Vals MMLU-Pro86.9%measured
MATH-50097.7%estimated ± 3.1 pp, medium confidence
MMMLU88.3%estimated ± 0.7 pp, medium confidence
Chess Puzzles20.0%measured
AIME 202596.6%estimated ± 1.8 pp, medium confidence
AA MMLU-Pro84.9%estimated ± 0.7 pp, high confidence
Gert Labs36.4%measured
AA-AnalystAgent46.5%estimated ± 3.7 pp, low confidence
AA Harvey LAB v1.084.0%estimated ± 1.2 pp, medium confidence
AA Tau3 Banking27.6%estimated ± 3.6 pp, low confidence
AA Terminal-Bench 2.180.3%estimated ± 2.5 pp, medium confidence
ApprenticeBench4.3%estimated ± 4.0 pp, high confidence
ARC-AGI-183.0%estimated ± 2.5 pp, medium confidence
ARC-AGI-236.2%estimated ± 9.7 pp, low confidence
CursorBench 3.131.2%estimated ± 3.4 pp, low confidence
CursorBench 3.255.9%estimated ± 3.6 pp, high confidence
EBR-bench19.9%estimated ± 9.1 pp, low confidence
Terminal-Bench 3.04.2%estimated ± 6.9 pp, low confidence
FrontierCode 1.1 Main13.8%estimated ± 4.3 pp, low confidence
FrontierMath v2 (Tier 4)6.5%estimated ± 4.0 pp, high confidence
FrontierMath v2 (Tiers 1-3)36.8%measured
FrontierSWE v212.8%estimated ± 8.3 pp, medium confidence
Furniture Assembly26.9%estimated ± 14.1 pp, low confidence
MaxxBench40.3%estimated ± 10.3 pp, low confidence
MazeBench0.1%estimated ± 2.7 pp, high confidence
Mystery Game Puzzles30.8%estimated ± 9.8 pp, medium confidence
NYT Connections77.7%measured
OSWorld-Verified70.4%estimated ± 3.8 pp, medium confidence
Terminal-Bench 4.110.4%estimated ± 14.9 pp, low confidence
Terminal-Bench Hard46.7%estimated ± 3.9 pp, high confidence
Vals SWE-bench76.4%measured
Terminal-Bench 2.1 (Vals AI)56.9%measured
VulcanBench v381.6%estimated ± 5.6 pp, low confidence
CWE-Bench-AA53.5%estimated ± 5.2 pp, medium confidence
AA Cyber Index16.6%estimated ± 9.2 pp, low confidence
DeepsecBench-AA11.6%estimated ± 8.2 pp, medium confidence
HealthBench Professional (length-adjusted, Artificial Analysis)53.8%estimated ± 4.3 pp, low confidence
HealthBench Professional (raw, Artificial Analysis)40.2%estimated ± 0.8 pp, low confidence
AA ITBench40.3%measured
Bug Hunt Bench11.8%estimated ± 7.2 pp, low confidence
CursorBench 4.034.4%estimated ± 3.3 pp, medium confidence
CWE-bench v143.1%estimated ± 5.7 pp, medium confidence
DeepSWE24.1%estimated ± 6.4 pp, low confidence
DRACO76.5%estimated ± 2.0 pp, medium confidence
FrontierCode 2.020.7%estimated ± 6.7 pp, low confidence
FrontierPhysics0.0%estimated ± 6.1 pp, low confidence
HLE w/o tools34.3%estimated ± 2.7 pp, medium confidence
OSWorld 2.06.3%estimated ± 6.9 pp, low confidence
OSWorld 2.128.1%estimated ± 3.6 pp, medium confidence
OSWorld 2.1 Offline8.0%estimated ± 1.9 pp, low confidence
PostTrainBench v1.121.0%estimated ± 3.7 pp, medium confidence
SpireClimb5.8%estimated ± 7.2 pp, medium confidence
StealthMark37.0%estimated ± 9.7 pp, low confidence
Toolathlon-Verified70.2%estimated ± 2.2 pp, low confidence
VulcanBench Frontier v475.0%estimated ± 6.8 pp, low confidence
AA AutomationBench41.9%estimated ± 7.9 pp, low confidence
GDP.pdf15.7%estimated ± 4.2 pp, high confidence
AA Terminal-Bench 4.03.0%estimated ± 13.7 pp, low confidence
ARC-AGI-30.0%estimated ± 8.3 pp, low confidence
ARC-AGI-3 Provider Adapter2.7%estimated ± 7.3 pp, low confidence
cursorBench4144.8%estimated ± 3.7 pp, medium confidence
CWE-bench37.9%estimated ± 6.2 pp, low confidence
MKA33.2%estimated ± 4.6 pp, medium confidence
SkillsBench official leaderboard (BenchFlow)58.4%measured
BinaryAudit43.8%estimated ± 12.0 pp, low confidence
OTelBench22.5%estimated ± 6.6 pp, medium confidence
Vibe Code Bench31.5%measured
FACTS Multimodal43.9%estimated ± 4.0 pp, high confidence
Hermes Bench69.0%estimated ± 1.8 pp, medium confidence
Hermes Index24.3%estimated ± 5.7 pp, low confidence
ExploitBench20.3%estimated ± 13.4 pp, low confidence
ExploitGym0.0%estimated ± 8.3 pp, low confidence
C-Eval93.5%estimated ± 0.9 pp, low confidence
Claw-Eval62.3%measured
DeepPlanning35.4%estimated ± 8.3 pp, low confidence
HMMT Feb 202592.5%estimated ± 1.8 pp, low confidence
HMMT Feb 202682.6%measured
HMMT Nov 202594.0%measured
MCP Atlas71.8%measured
MCP-Tasks74.4%estimated ± 3.6 pp, medium confidence
MMAnswerBench83.8%measured
MMLU-Redux94.0%estimated ± 0.8 pp, medium confidence
NL2Repo42.7%measured
PostTrainBench v119.0%estimated ± 3.1 pp, medium confidence
QwenClawBench60.5%estimated ± 2.6 pp, high confidence
SuperGPQA71.4%estimated ± 7.2 pp, medium confidence
Terminal-Bench 2.063.5%measured
Toolathlon38.2%estimated ± 4.2 pp, high confidence
AA LiveCodeBench89.6%estimated ± 2.6 pp, high confidence
HealthBench Hard23.0%estimated ± 8.6 pp, low confidence
LiveCodeBench Pro82.5%estimated ± 6.0 pp, low confidence
MedXpertQA (Text)44.2%estimated ± 4.5 pp, low confidence
MMLU-Pro (Arcee)85.6%estimated ± 3.4 pp, medium confidence
React Native Evals75.8%estimated ± 3.0 pp, medium confidence
ResearchClawBench18.2%measured
SWE-Rebench62.7%measured
PostTrainBench18.5%estimated ± 3.7 pp, medium confidence
DAYJOB0.4%estimated ± 6.3 pp, medium confidence
DAYJOB Healthcare0.1%estimated ± 6.1 pp, low confidence
Finance Agent v255.2%estimated ± 2.4 pp, low confidence
BioMysteryBench (human-solvable)81.8%estimated ± 0.6 pp, low confidence
FrontierCode 1.1 Extended55.5%estimated ± 3.0 pp, low confidence
HealthBench (raw)39.0%estimated ± 6.0 pp, low confidence
HealthBench (length-adjusted)49.8%estimated ± 3.4 pp, low confidence
HealthBench Professional56.8%estimated ± 4.2 pp, low confidence
HealthBench Professional (raw)50.2%estimated ± 4.5 pp, medium confidence
HLE-Verified0.3%estimated ± 4.6 pp, low confidence
LABBench281.4%estimated ± 1.8 pp, low confidence
ScarfBench25.2%estimated ± 9.1 pp, low confidence
BlenderWorld (text-only)70.6%estimated ± 4.0 pp, low confidence
Cookie-Bench77.0%estimated ± 2.5 pp, low confidence
STEMBench2.4%estimated ± 0.2 pp, low confidence
SimpleQA23.2%estimated ± 4.3 pp, medium confidence
Agents' Last Exam23.6%estimated ± 3.3 pp, low confidence
OpenHarmony Bench v1.052.3%measured
SEC-Bench Pro30.5%estimated ± 12.3 pp, low confidence
IMOAnswerBench79.1%estimated ± 5.6 pp, medium confidence
MRCRv282.9%estimated ± 11.3 pp, low confidence
MMLongBench-Doc61.1%estimated ± 2.6 pp, low confidence
BioBasicsBench33.9%estimated ± 2.8 pp, low confidence
LifeVal53.7%estimated ± 1.6 pp, medium confidence
ExploitBench Internal Port0.0%estimated ± 1.4 pp, low confidence
PinchBench89.5%estimated ± 3.6 pp, medium confidence