Skip to content
aiqbench

Nvidia · model passport

Nemotron 3 Ultra

nemotron-3-ultra
  • Open weights
  • OpenMDW-1.1 licence
  • Released 2026-10-16(first seen on LMArena)
3/27axes covered
Best percentile
69.2GPQA Diamond
Cohort standing
49.2median 60.8

What the data says

Benchmarked on 3 of 27 tracked axes. Every figure below is the model's own published result on that board.

Weakest axes

  • 9.1 pct — Agent Arena (-0.089)

Uneven: 60.1 percentile points between its best and worst axis — 69.2 pct on GPQA Diamond versus 9.1 pct on Agent Arena.

  • GPQA Diamond69.2 pct85.4%Verify →
  • AIME (math)67 pct86.7%Verify →
  • Agent Arena9.1 pct-0.089Verify →
  • OverallNot benchmarked
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • IFBench (Artificial Analysis)Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • Terminal-BenchNot benchmarked
  • CodingNot benchmarked
  • Instruction followingNot benchmarked
  • Hard promptsNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

  • Nemotron 3 Ultra stands at 49.2 (raw mean 48.4) — measured on 3 of 27 axes.

    standingtemplateVerify →

  • Nemotron 3 Ultra stands at 49.2 versus a cohort median of 60.8 across 168 models released within 180 days — below the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →