VerdictPal
Join

Models / NVIDIA

Nemotron 3 Ultra 550B A55B (Reasoning)

Nemotron · Released 2026-06-04

NVIDIA's open reasoning MoE, evaluated by Artificial Analysis on 4 Jun. Public catalogs describe 550B total / 55B active parameters and a 262K context window; VerdictPal keeps score claims in the benchmark ledger.

Open reasoning and orchestration model for teams already in NVIDIA's inference stack or testing large open MoEs.

#28 of 51 on AA Index · current snapshot
38 AA Index · 10 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite51
Context262K
Input / 1M—
Output / 1M—
Knowledge cutoffopen
Output speed215 t/s
TTFT (default API)0.88s
Statuslightweight
ReasoningCodingAgenticLong context
Reasoning
87
Coding
40
Agentic
54
Long context
67

62average across 4 tested families

Benchmark placements

Where Nemotron 3 Ultra 550B A55B (Reasoning) places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
IFBenchReasoning#2/ 5781Artificial Analysis2026-07-21
AA output speedPerformance#9/ 69Artificial Analysis2026-07-21
AA-LCRLong context#32/ 6467Artificial Analysis2026-07-21
GPQA DiamondReasoning#38/ 6987Artificial Analysis2026-07-21
Artificial Analysis Intelligence IndexReasoning#39/ 6738Artificial Analysis2026-07-21
Humanity's Last ExamReasoning#41/ 6527Artificial Analysis2026-07-21
Terminal-BenchAgentic#43/ 6954Artificial Analysis2026-07-21
AA time to first tokenPerformance#47/ 69Artificial Analysis2026-07-21
τ³-Bench BankingAgentic#50/ 6414Artificial Analysis2026-07-21
SciCodeCoding#52/ 6540Artificial Analysis2026-07-21
Family context

The three highest-scoring carded models in each capability family. Where Nemotron 3 Ultra 550B A55B (Reasoning) shows up, it's highlighted.

ReasoningNemotron 3 Ultra 550B A55B (Reasoning) · 87
  1. 1
    Claude Mythos Preview
    95
  2. 2
    GPT-5.6 Sol
    94
  3. 3
    Kimi K3
    94
CodingNemotron 3 Ultra 550B A55B (Reasoning) · 40
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticNemotron 3 Ultra 550B A55B (Reasoning) · 54
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextNemotron 3 Ultra 550B A55B (Reasoning) · 67
  1. 1
    Kimi K3
    75
  2. 2
    GPT-5.1
    75
  3. 3
    GPT-5.6 Sol
    74
Newest receipts

Benchmark rows added to the public ledger for Nemotron 3 Ultra 550B A55B (Reasoning) in the last 120 days. Older rows live in the full table below.

10 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context67%Artificial Analysis2
AA output speedPerformance215 t/sArtificial Analysis2
AA time to first tokenPerformance0.88sArtificial Analysis2
Artificial Analysis Intelligence IndexReasoning37.8%Artificial Analysis2
GPQA DiamondReasoning86.7%Artificial Analysis2
Humanity's Last ExamReasoning26.6%Artificial Analysis2
IFBenchReasoning81.36%Artificial Analysis2
SciCodeCoding39.9%Artificial Analysis2
τ³-Bench BankingAgentic13.81%Artificial Analysis2
Terminal-BenchAgentic53.93%Artificial Analysis2
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Reasoning87
Coding40
Agentic54
Long context67
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMiniMaxxAIMetaZhipuXiaomiMeituanCohere

Full benchmark ledger

Every catalog benchmark for Nemotron 3 Ultra 550B A55B (Reasoning). Scores link to the original source; gaps mean no public row exists yet.

10 sourced rows

10 of 32 catalog benchmarks have a sourced row for Nemotron 3 Ultra 550B A55B (Reasoning).

Reasoning

Coding

Agentic

Long context

Performance

Sources