benchgap
MiniMax · model

MiniMax-VL-01 benchmark scores

As of 2026-11-19, MiniMax-VL-01 (MiniMax) has measured scores on 2 benchmarks and estimated scores on 21 more.

BenchmarkScoreSource
AA-MMMU-Pro52.3%estimated ± 1.5 pp, high confidence
MMMU68.5%measured
ParseBench-136.2%estimated ± 8.4 pp, medium confidence
ParseBench-238.6%estimated ± 5.0 pp, medium confidence
CharXiv44.8%estimated ± 5.1 pp, low confidence
CharXiv w/o tools70.6%estimated ± 2.1 pp, high confidence
AI2D_TEST88.4%estimated ± 2.0 pp, high confidence
CountBench92.7%estimated ± 3.0 pp, high confidence
DynaMath79.8%estimated ± 5.3 pp, low confidence
ERQA47.1%estimated ± 5.2 pp, low confidence
MathVision58.8%estimated ± 2.9 pp, high confidence
MLVU (M-Avg)74.5%estimated ± 2.2 pp, high confidence
MMMU-Pro52.7%measured
RealWorldQA78.4%estimated ± 2.8 pp, high confidence
ScreenSpot Pro55.3%estimated ± 7.9 pp, low confidence
SimpleVQA50.8%estimated ± 7.1 pp, medium confidence
Video-MME (w/o subtitle)70.6%estimated ± 1.2 pp, high confidence
Video-MME (with subtitle)72.8%estimated ± 3.0 pp, high confidence
VideoMMMU65.7%estimated ± 2.3 pp, high confidence
We-Math74.1%estimated ± 7.2 pp, low confidence
MMVU59.6%estimated ± 2.7 pp, medium confidence
OCRBench V262.4%estimated ± 3.3 pp, high confidence
MMMU-Pro w/ Python62.6%estimated ± 2.6 pp, medium confidence