BenchLeader

Nemotron 3 Ultra

Reasoning effort

Nemotron 3 Ultra is a NVIDIA proprietary model, released 4 Jun 2026. Its best configuration ranks #548 of 785 on the BenchLeader Index at 44.1 ±10.6, in the lower half. The ± is the point: 528 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in reasoning (62) and lowest in agents & tools (23). It has been measured at 2 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 20 Oct 2026.

Blended price
–
Output speed
–
First answer
–
Context
–
Full answer
–
Cost per run
–
Released
4 Jun 2026
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index44
  2. Reasoning62
  3. Coding36
  4. Agents & tools23
  5. Maths46

Versions

NVIDIA has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

ModelReleasedIndexRank
Nemotron 3 Ultrathis page4 Jun 202644.1#548
Nemotron Ultra 3–––

Reasoning-effort configurations

The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.

EffortIndexRankSpeedFirst answerChat reply costCategories
thinking–––––Agents & tools 40
not statedbest44.1#548–––Agents & tools 23 · Coding 36 · Maths 46 · Reasoning 62

How its index has moved

8 Sept 2026 to 21 Oct 2026
344760

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmarknot statedSourceTrend
GPQA Diamond85.3%#88Epoch AI Benchmarking Hub
Mystery Game Puzzlesnot in index20.0%#60Epoch AI Benchmarking Hub
LMCAnot in index36.9%#121Epoch AI Benchmarking Hub
DTBenchnot in index90.1%#82Epoch AI Benchmarking Hub

Coding

Benchmarknot statedSourceTrend
SciCode40.3%#160SciCode
WeirdML43.5%#89WeirdML
FrontierCode13.6%#42Cognition

Agents & tools

Benchmarkthinkingnot statedSourceTrend
APEX-Agentseffort not stated–22.7%#52Mercor
Arena Agenteffort not stated–-12.3#48Arena (LMArena)
MCP Atlas63.1%#25–Scale AI SEAL

Maths

Benchmarknot statedSourceTrend
OTIS Mock AIME86.7%#86Epoch AI Benchmarking Hub
ProofBench2.0%#76Vals AI

Composite

Benchmarknot statedSourceTrend
Epoch Capabilities Indexnot in index146.0#79Epoch AI Benchmarking Hub

More from NVIDIA

New this month

See also

Questions people ask

What are Nemotron 3 Ultra's benchmark scores?
As of 24 Oct 2026, Nemotron 3 Ultra scores 44.1 ±10.6 on the BenchLeader Index, strongest in reasoning (62) and weakest in agents & tools (23). That rests on 8 independent benchmark results, and every score on this page links to its publisher.
How does Nemotron 3 Ultra rank?
Nemotron 3 Ultra is #548 of 785 ranked configurations on 24 Oct 2026. 528 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
When was Nemotron 3 Ultra released?
NVIDIA released Nemotron 3 Ultra on 4 Jun 2026. BenchLeader has results for it at 2 reasoning-effort settings.

Data as of 24 Oct 2026. Compare these configurations.

Cite as: BenchLeader, “Nemotron 3 Ultra: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/nemotron-3-ultra.