benchgap
Zhipu (GLM) · model

GLM-4.7-Flash benchmark scores

As of 2026-11-21, GLM-4.7-Flash (Zhipu (GLM)) has measured scores on 4 benchmarks and estimated scores on 37 more.

BenchmarkScoreSource
AA-GPQA Diamond73.2%estimated ± 6.2 pp, medium confidence
AA-HLE11.9%estimated ± 5.7 pp, medium confidence
AA-SciCode38.2%estimated ± 3.8 pp, high confidence
AIME2690.8%estimated ± 4.3 pp, medium confidence
Artificial Analysis Intelligence Index11.0%estimated ± 7.4 pp, medium confidence
CritPt0.4%estimated ± 4.0 pp, high confidence
GPQA Diamond75.4%estimated ± 1.2 pp, high confidence
HLE12.4%estimated ± 6.5 pp, medium confidence
LiveCodeBench v664.0%measured
AA-Omniscience Accuracy19.7%estimated ± 8.5 pp, medium confidence
SciCode37.6%estimated ± 3.6 pp, high confidence
AA Coding Index27.7%estimated ± 5.3 pp, medium confidence
SWE-bench Verified59.2%measured
SWE-bench Pro35.5%estimated ± 4.5 pp, high confidence
MMLU-Pro82.3%estimated ± 4.4 pp, high confidence
AIME 202492.7%estimated ± 2.6 pp, high confidence
GPQA75.2%measured
MMLU88.0%estimated ± 4.2 pp, high confidence
Vals GPQA Diamond73.1%estimated ± 4.5 pp, high confidence
Vals LiveCodeBench59.0%estimated ± 10.0 pp, low confidence
Vals MMLU-Pro81.1%estimated ± 2.3 pp, high confidence
MATH-50098.4%estimated ± 2.0 pp, high confidence
MMMLU85.1%estimated ± 1.7 pp, high confidence
AIME 202591.6%measured
AA MMLU-Pro85.6%estimated ± 1.2 pp, low confidence
ARC-AGI-136.3%estimated ± 6.7 pp, low confidence
ARC-AGI-20.0%estimated ± 10.9 pp, low confidence
Vals SWE-bench48.2%estimated ± 6.6 pp, low confidence
DeepSWE13.0%estimated ± 12.7 pp, low confidence
HLE w/o tools12.0%estimated ± 5.3 pp, medium confidence
Vibe Code Bench0.0%estimated ± 8.4 pp, low confidence
C-Eval89.8%estimated ± 1.2 pp, high confidence
HMMT Feb 202594.8%estimated ± 2.9 pp, high confidence
HMMT Feb 202675.9%estimated ± 11.0 pp, low confidence
MMLU-Redux91.7%estimated ± 1.7 pp, high confidence
NL2Repo11.2%estimated ± 6.2 pp, low confidence
SuperGPQA55.1%estimated ± 8.5 pp, low confidence
React Native Evals70.3%estimated ± 2.7 pp, low confidence
SWE-Rebench57.0%estimated ± 3.6 pp, low confidence
SimpleQA38.6%estimated ± 13.4 pp, low confidence
LiveCodeBench65.4%estimated ± 14.6 pp, low confidence