The LLM benchmark aggregator.

NVIDIA Nemotron 3 Nano 30B A3B

NVIDIA · 32B · A3B · open weights

Strongest in Factual grounding (#54 of 101), weakest in Agents (#249 of 267). Above par in 2 of 4 scopes. Among the models it meets almost everywhere, it finishes behind GPT-6 Astra and GPT-6 Sol and ahead of Claude Opus 4.5 and Grok 4.1 Fast.

§ 1 · Profile

What it is good at

Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.

Safety50.3−11.2#173/3361/3

Factual grounding50.9−19.7#54/1011/1

Agents39−29.1#249/2672/5

Knowledge work35.7−37.9#156/1772/2

§ 2 · Head to head

What it beats, and what beats it

The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for NVIDIA Nemotron 3 Nano 30B A3B, left for the other.

Llama 3.1 8B Instructwon 3 · lost 0

Ministral 3 3Bwon 4 · lost 0

Phi-4 Mini Instructwon 4 · lost 0

Ministral 3 8Bwon 4 · lost 0

DeepSeek V3won 3 · lost 1

Gemma 4 E2Bwon 2 · lost 1

Mistral Mediumwon 2 · lost 1

Grok 4.1 Fastwon 2 · lost 1

Claude Opus 4.5won 2 · lost 1

Gemma 3 27B Itwon 2 · lost 2

Gemma 3 12B Itwon 2 · lost 2

Ministral 3 14Bwon 2 · lost 2

DeepSeek R1won 2 · lost 2

Llama 4 Scout Instructwon 2 · lost 2

Mistral Large 3won 2 · lost 2

Mercury 2won 2 · lost 2

Gemini 3.1 Prowon 2 · lost 2

Kimi K2.5won 2 · lost 2

Kimi K2.6won 2 · lost 2

GPT-4.1 Nanowon 1 · lost 2

Gemma 4 E4Bwon 1 · lost 2

Gemma 3 4B Itwon 1 · lost 2

Gemma 4 12Bwon 1 · lost 2

NVIDIA Nemotron 3 Super 120B A12Bwon 1 · lost 2

Ling 3.0 Flashwon 1 · lost 2

Mistral Smallwon 1 · lost 2

Grok 4.3won 1 · lost 2

Gemini 3.5 Flashwon 1 · lost 2

Nemotron 3 Ultra 550B A55Bwon 1 · lost 2

Kimi K2.7 Codewon 1 · lost 2

Mimo V2.5 Prowon 1 · lost 2

Command Awon 1 · lost 2

Grok Build 0.1won 1 · lost 2

Qwen3.7 Maxwon 1 · lost 2

Ling 3.0 Flash VLwon 1 · lost 2

Gemini 3.6 Flashwon 1 · lost 2

GPT-5 Nanowon 1 · lost 2

O4 Miniwon 1 · lost 2

GPT-5.2won 1 · lost 2

Kimi K2won 1 · lost 2

GLM-5.2won 1 · lost 2

DeepSeek V4 Flashwon 1 · lost 2

MiniMax M3won 1 · lost 2

GLM-5.3 Flashwon 1 · lost 2

Gemini 3 Prowon 1 · lost 2

Llama 4 Maverick Instructwon 1 · lost 3

Gemini 2.5 Prowon 1 · lost 3

Gemma 4 31Bwon 1 · lost 3

Qwen3 8Bwon 1 · lost 3

Qwen3.5 122B A10Bwon 1 · lost 3

Qwen3.5 35B A3Bwon 1 · lost 3

GPT OSS 120Bwon 1 · lost 3

Claude Sonnet 4won 1 · lost 3

GPT-5 Miniwon 1 · lost 3

GPT-5.1won 1 · lost 3

GPT-5won 1 · lost 3

Claude Haiku 4.5won 1 · lost 3

DeepSeek V3.2won 1 · lost 3

Claude Sonnet 4.5won 1 · lost 3

Claude Sonnet 4.6won 1 · lost 3

Claude Opus 4.7won 1 · lost 3

GLM-4.6won 1 · lost 3

GPT-5.6 Solwon 1 · lost 3

Ministral 8Bwon 0 · lost 3

O3 Miniwon 0 · lost 3

GPT-4o Miniwon 0 · lost 3

GPT-4won 0 · lost 3

Nova Microwon 0 · lost 3

Claude 3.5 Haikuwon 0 · lost 3

Nova Prowon 0 · lost 3

GPT OSS 20Bwon 0 · lost 3

Phi 4won 0 · lost 3

Qwen3.5 397B A17Bwon 0 · lost 3

Qwen3 4B Instructwon 0 · lost 3

Gemini 2.5 Flash Litewon 0 · lost 3

GPT-4.1 Miniwon 0 · lost 3

Mistral Largewon 0 · lost 3

MiniMax M2.7won 0 · lost 3

Inklingwon 0 · lost 3

Hy3won 0 · lost 3

GLM-5.1won 0 · lost 3

Grok 4.5won 0 · lost 3

Qwen3 235B A22B Instructwon 0 · lost 3

GPT-4.1won 0 · lost 3

Gemini 2.5 Flashwon 0 · lost 3

Muse Spark 1.1won 0 · lost 3

Gemini 3.8 Flashwon 0 · lost 3

GPT-6 Lunawon 0 · lost 3

Claude Opus 4.8won 0 · lost 3

GPT-5.6 Terrawon 0 · lost 3

GPT-5.6 Lunawon 0 · lost 3

Claude Sonnet 5won 0 · lost 3

Grok 4.6won 0 · lost 3

Mimo V2.6 Prowon 0 · lost 3

Qwen3.8 Maxwon 0 · lost 3

Grok 4.7won 0 · lost 3

Claude Opus 5won 0 · lost 3

Claude Opus 5.5won 0 · lost 3

Trinity Largewon 0 · lost 4

Gemini 3.1 Flash Litewon 0 · lost 4

Qwen3 Next 80B A3B Thinkingwon 0 · lost 4

Nova 2 Litewon 0 · lost 4

Qwen3 14Bwon 0 · lost 4

Qwen3 32Bwon 0 · lost 4

Gemma 4 26B A4Bwon 0 · lost 4

GPT-5.4 Nanowon 0 · lost 4

GPT-5.4 Miniwon 0 · lost 4

GPT-5.4won 0 · lost 4

GPT-5.5won 0 · lost 4

DeepSeek V4 Prowon 0 · lost 4

GPT-6 Solwon 0 · lost 4

GPT-6 Astrawon 0 · lost 4

§ 3 · Sources

Where the numbers come from

3 publications, 3 figures. Every one links to the page it was read from.

GDPval-AA ↗1 measureread 2026-09-27

GDPval-AA 241

AA-Briefcase ↗1 measureread 2026-09-27

AA-Briefcase 80

Vectara Hallucination Leaderboard ↗1 measureread 2026-09-27

Vectara · Factual consistency 90.4%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=nvidia-nemotron-3-nano-30b-a3b)](https://publicai.io/model-index/m/nvidia-nemotron-3-nano-30b-a3b)