benchgap
NVIDIA · model

Nemotron 3 Super 100B benchmark scores

As of 2026-11-22, Nemotron 3 Super 100B (NVIDIA) has measured scores on 7 benchmarks and estimated scores on 37 more.

BenchmarkScoreSource
AA-GPQA Diamond77.2%estimated ± 6.2 pp, medium confidence
AA-HLE15.2%estimated ± 5.7 pp, medium confidence
AA-SciCode38.9%estimated ± 3.8 pp, high confidence
AIME2694.3%estimated ± 1.0 pp, medium confidence
Artificial Analysis Intelligence Index12.7%estimated ± 7.4 pp, medium confidence
CritPt0.5%estimated ± 4.0 pp, high confidence
GPQA Diamond79.4%estimated ± 1.2 pp, high confidence
HLE18.3%measured
AA-Omniscience Accuracy20.7%estimated ± 8.5 pp, medium confidence
SciCode38.2%estimated ± 3.6 pp, high confidence
AA Coding Index28.6%estimated ± 5.3 pp, medium confidence
SWE-bench Verified60.5%measured
SWE-bench Pro36.9%estimated ± 4.5 pp, high confidence
MMLU-Pro83.7%measured
AIME 202492.0%estimated ± 2.6 pp, high confidence
BBH98.1%estimated ± 2.8 pp, medium confidence
GPQA79.2%measured
MMLU90.1%estimated ± 2.1 pp, high confidence
Vals GPQA Diamond77.1%estimated ± 4.5 pp, high confidence
Vals LiveCodeBench60.2%estimated ± 10.0 pp, low confidence
Vals MMLU-Pro82.7%estimated ± 2.3 pp, high confidence
MATH-50098.3%estimated ± 2.0 pp, high confidence
MMMLU86.7%estimated ± 1.7 pp, high confidence
AIME 202590.2%measured
AA MMLU-Pro86.0%estimated ± 1.2 pp, low confidence
ARC-AGI-148.9%estimated ± 6.7 pp, low confidence
ARC-AGI-20.0%estimated ± 10.9 pp, low confidence
Vals SWE-bench49.9%estimated ± 6.6 pp, low confidence
DeepSWE14.5%estimated ± 12.7 pp, low confidence
HLE w/o tools13.4%estimated ± 5.3 pp, medium confidence
Vibe Code Bench0.0%estimated ± 8.4 pp, low confidence
C-Eval88.5%estimated ± 0.9 pp, low confidence
Claw-Eval5.5%measured
HMMT Feb 202593.7%measured
HMMT Feb 202685.6%estimated ± 1.2 pp, medium confidence
HMMT Nov 202591.9%estimated ± 1.5 pp, high confidence
MMAnswerBench81.4%estimated ± 2.0 pp, low confidence
MMLU-Redux92.5%estimated ± 0.6 pp, high confidence
NL2Repo12.5%estimated ± 6.2 pp, low confidence
SuperGPQA59.4%estimated ± 7.2 pp, medium confidence
React Native Evals70.9%estimated ± 2.7 pp, low confidence
SWE-Rebench57.0%estimated ± 3.6 pp, low confidence
SimpleQA37.9%estimated ± 11.7 pp, low confidence
LiveCodeBench66.3%estimated ± 14.6 pp, low confidence