Translate
Independent model intelligence

Find the right AI model,
not just the loudest one.

Compare current model capability, context, modalities, public preference and API economics in one continuously refreshed decision surface.

LiveBench 2.0 LMArena models.dev OpenRouter AIHOT cross-check
Back to leaderboard
NVIDIA · Active

NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)

nemotron family · launched 2026-06-04

ReasoningToolsStructuredOpen weights
AITopic score56.0#76 overall

Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy

Evidence coverage5%1 evaluations · 1 institutions
Context / maximum output131.1k / 32ktokens
Cache / input / output$0.12 · $0.1 · $0.1USD per million tokens
Value / freshness80.7 / 69relative value · release freshness
Product profile

What this model supports

Inputtext
Outputtext
Knowledge cutoff2025-09
WeightsOpen weights
Capability profile

Strengths by domain

Coding—0 public results
Research & reasoning—0 public results
Professional work—0 public results
Knowledge & instruction—0 public results
Behind the score

Every result has a source

Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.

Human preference & indices2 results

AA IndexArtificial Analysis64.24 indexReading 56.0

Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)Open evidence
Arena TextLMArena1,445.2 EloReading 56.0

Direct LMArena text leaderboard result.

Open evidence
Same builder

More from NVIDIA