Nemotron-Cascade-2-30B-A3B

Released
2026-03-19
Last refreshed
2026-05-14
Status
Researched 139d ago
Open weightsCommercial use: conditionalCodingAgentsLong contextClassification

Nemotron-Cascade-2-30B-A3B is a released coding, agents, and long context model with open-weight and 1.05m context; evaluate it while provider pricing coverage matures.

NVIDIA AI releases · 19 in the last 12 months · this family litChangelog →
Specifications
Released
2026-03-19
Context
1.05m
Parameters
30B
Architecture
Decoder Only
Specialization
general
Openness
Open weights
License
Llama 3 CommunityCommercial use: conditional
Weights
Available
Code
Unknown
Created by

Accelerated AI for enterprise solutions

Santa Clara, California, United States
Founded 2015
Website
Pricing

No tracked provider token pricing is available yet.

About

30B MoE model with 3B active parameters - superior reasoning with IMO/IOI 2025 gold-medal performance

Provider price ladder

No tracked provider token pricing is available for this model yet.

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Coding

Benchmark scores(5)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
AIME 202592.4AIME 2025 (accuracy)Observed 2026-06-07—Source
Google-Proof Q&A76.1GPQA Diamond (accuracy)Observed 2026-06-07—Source
LiveCodeBench87.2LiveCodeBench v6 (accuracy)Observed 2026-06-07—Source
MMLU PRO79.8From Nemotron-Cascade-2 technical paper Table 1 (accuracy)Observed 2026-06-07—Source
SWE-bench Verified50.2SWE Verified with OpenHands (resolved)Observed 2026-06-07—Source

Migration checks

No linked migration route is available for this model yet.