benchgap
MiniMax · model

MiniMax-Text-01 benchmark scores

As of 2026-11-19, MiniMax-Text-01 (MiniMax) has measured scores on 4 benchmarks and estimated scores on 16 more.

BenchmarkScoreSource
AA-GPQA Diamond52.2%estimated ± 6.2 pp, medium confidence
AA-HLE3.0%estimated ± 5.7 pp, medium confidence
Artificial Analysis Intelligence Index11.2%estimated ± 3.2 pp, medium confidence
CritPt0.3%estimated ± 4.0 pp, high confidence
GPQA Diamond54.8%estimated ± 1.2 pp, high confidence
HLE3.3%estimated ± 6.5 pp, low confidence
AA-Omniscience Accuracy21.7%estimated ± 2.4 pp, high confidence
MMLU-Pro75.7%measured
BBH93.9%estimated ± 2.4 pp, low confidence
GPQA54.4%measured
MMLU88.5%measured
Vals GPQA Diamond52.4%estimated ± 4.5 pp, high confidence
Vals MMLU-Pro70.9%estimated ± 2.3 pp, high confidence
MMMLU75.2%estimated ± 1.7 pp, high confidence
AA MMLU-Pro83.8%estimated ± 1.2 pp, low confidence
HLE w/o tools11.6%estimated ± 5.1 pp, low confidence
C-Eval83.5%estimated ± 1.2 pp, medium confidence
MMLU-Redux87.8%estimated ± 0.6 pp, high confidence
SuperGPQA56.1%estimated ± 12.4 pp, low confidence
SimpleQA23.7%measured