NNemotron Ultra 3
nemotron family · launched 2026-06-04
ReasoningToolsStructuredOpen weightsLargest Nemotron 3 model for maximum open-weight reasoning and agent accuracy
What this model supports
Strengths by domain
Every result has a source
Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.
Coding1 results
LiveBench 2.0 · CodingLiveBench43.60 scoreReading 43.6
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0Open evidenceResearch & reasoning1 results
LiveBench 2.0 · ResearchLiveBench74.70 scoreReading 74.7
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0Open evidenceProfessional work1 results
LiveBench 2.0 · ProfessionalLiveBench31.08 scoreReading 31.1
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Professional = long-agentic, browser, data-analysis and design average.
Configuration: LiveBench 2.0Open evidenceKnowledge & instruction1 results
LiveBench 2.0 · KnowledgeLiveBench43.20 scoreReading 43.2
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Knowledge uses the published LiveBench research suite.
Configuration: LiveBench 2.0Open evidenceHuman preference & indices2 results
LiveBenchLiveBench40.83 scoreReading 40.8
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0Open evidenceAA IndexArtificial Analysis40.83 indexReading 5.0
Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0Open evidence