RLTasksby ulam.ai
Models / NVIDIA

NVIDIA / MODEL EVIDENCE

Nemotron 3 Ultra

27 benchmarks · 28 observations · 28 sources · released 2026-06-04

Scores at a glance

27 benchmarks · large dot: Nemotron 3 Ultra; small dots: closest models where reported

CritPt ↗3.14%
032.29

Nemotron 3 Ultra · CritPt · Accuracy · % ↗

LMCA ↗36.9%
2.7868.26

Nemotron 3 Ultra · LMCA · Score · % ↗

DTBench ↗90.13%
41.6598.93

Nemotron 3 Ultra · DTBench · Accuracy · % ↗

SciCode ↗40.28%
1.2766.9

Nemotron 3 Ultra · SciCode · Score · % ↗

MedCode ↗38.62 %
19.7263.57

Nemotron 3 Ultra · MedCode · Accuracy ↗

MCP Atlas ↗63.10%
40.288.1

Nemotron 3 Ultra (thinking) · Scale Labs · Score ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

8.2 percentile-point gap

12 of 18 shared benchmark comparisons

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. SciCode Benchmark | Artificial Analysis ↗

    Artificial Analysis

  2. FrontierCode Leaderboard ↗

    Cognition

  3. DTBench — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  4. LMCA — Conceptual Reasoning Index ↗

    Conceptual Reasoning Index

  5. APEX-Agents ↗

    Epoch AI

  6. CritPt v1 ↗

    Epoch AI

  7. GPQA Diamond ↗

    Epoch AI

  8. Mystery Game Puzzles ↗

    Epoch AI

  9. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  10. AI benchmarks & capabilities ↗

    Epoch AI

  11. WeirdML ↗

    Håvard Tveit Ihle

  12. Scale Labs — evaluation methodology and results ↗

    Scale Labs / SEAL · 2026

  13. Code Migration v1 — evaluation methodology and results ↗

    Vals AI · 2026

  14. CorpFin — evaluation methodology and results ↗

    Vals AI · 2026

  15. Excel Modeling Benchmark v1 — evaluation methodology and results ↗

    Vals AI · 2026

  16. Finance Agent v2 — evaluation methodology and results ↗

    Vals AI · 2026

  17. GPQA Diamond — evaluation methodology and results ↗

    Vals AI · 2026

  18. Harvey's Legal Agent Benchmark v1 — evaluation methodology and results ↗

    Vals AI · 2026

  19. LiveCodeBench — evaluation methodology and results ↗

    Vals AI · 2026

  20. LegalBench — evaluation methodology and results ↗

    Vals AI · 2026

  21. Legal Research Bench — evaluation methodology and results ↗

    Vals AI · 2026

  22. MedCode — evaluation methodology and results ↗

    Vals AI · 2026

  23. MMLU Pro — evaluation methodology and results ↗

    Vals AI · 2026

  24. ProgramBench — evaluation methodology and results ↗

    Vals AI · 2026

  25. ProofBench — evaluation methodology and results ↗

    Vals AI · 2026

  26. SWE-bench Verified — evaluation methodology and results ↗

    Vals AI · 2026

  27. TaxEval — evaluation methodology and results ↗

    Vals AI · 2026

  28. Vibe Code Bench — evaluation methodology and results ↗

    Vals AI · 2026

Names used in source tables

Nemotron 3 Ultra · Nemotron 3 Ultra (Mini-SWE-agent) · Nemotron 3 Ultra (OpenHands) · Nemotron 3 Ultra (thinking)