Skip to content
aiqbench

Nvidia · model passport

Nvidia Nemotron 3 Ultra 550b A55b

nvidia-nemotron-3-ultra-550b-a55b
  • Open weights
  • OpenMDW-1.1 licence
  • Released 2026-10-28(first seen on LMArena (approximate))
5/27axes covered
Overall · LMArena
1,427#117 of 469
Best percentile
75.3Overall
Cohort standing
61.1median 57.4

What the data says

Benchmarked on 5 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 30.5 percentile points between its best and worst axis — 75.3 pct on Overall versus 44.8 pct on Factuality Arena.

  • Overall75.3 pct1,427Verify →
  • Coding74.7 pct1,474Verify →
  • Hard prompts73.1 pct1,444Verify →
  • Instruction following70.6 pct1,406Verify →
  • Factuality Arena44.8 pct1,432Verify →
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not 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

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.

  • NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4) from nvidia covers 5 of 27 axes with a composite score of 67.7 and a shrunk score of 61.1, without thin coverage.

    standingVerify →

  • NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4) from nvidia achieved a standing of 61.1, which is above the cohort median of 57.4 across 215 models within an 180-day window.

    cohortVerify →

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 →