benchgap
Zhipu (GLM) · model

GLM-4.6V benchmark scores

As of 2026-11-19, GLM-4.6V (Zhipu (GLM)) has measured scores on 4 benchmarks and estimated scores on 20 more.

BenchmarkScoreSource
AA-MMMU-Pro65.3%estimated ± 1.5 pp, high confidence
MMMU76.0%measured
ParseBench-145.8%estimated ± 8.4 pp, medium confidence
ParseBench-253.2%estimated ± 5.0 pp, medium confidence
CharXiv61.7%estimated ± 5.1 pp, medium confidence
CharXiv w/o tools73.4%estimated ± 2.1 pp, high confidence
AI2D_TEST89.7%estimated ± 2.0 pp, high confidence
CountBench94.1%estimated ± 3.0 pp, high confidence
DynaMath82.5%estimated ± 5.3 pp, low confidence
ERQA47.1%estimated ± 5.2 pp, low confidence
MathVision73.6%estimated ± 2.9 pp, high confidence
MLVU (M-Avg)80.5%estimated ± 2.2 pp, high confidence
MMMU-Pro66.0%measured
RealWorldQA81.2%estimated ± 2.8 pp, high confidence
ScreenSpot Pro55.3%estimated ± 7.9 pp, low confidence
SimpleVQA57.0%estimated ± 7.1 pp, medium confidence
Video-MME (w/o subtitle)76.8%estimated ± 1.2 pp, high confidence
Video-MME (with subtitle)80.9%estimated ± 3.0 pp, high confidence
VideoMMMU74.7%measured
We-Math77.8%estimated ± 7.2 pp, low confidence
MedXpertQA (MM)40.9%estimated ± 2.4 pp, medium confidence
MMVU69.4%estimated ± 2.7 pp, medium confidence
OCRBench V265.1%measured
MMMU-Pro w/ Python72.7%estimated ± 2.6 pp, medium confidence