What are Nemotron 3 Nano Omni 30B A3B's benchmark scores?

As of 25 Oct 2026, Nemotron 3 Nano Omni 30B A3B (thinking effort) scores 45.1 ±6.4 on the BenchLeader Index, strongest in instruction following (63) and weakest in knowledge (36). That rests on 7 independent benchmark results, and every score on this page links to its publisher.

How does Nemotron 3 Nano Omni 30B A3B rank?

Nemotron 3 Nano Omni 30B A3B (thinking effort) is #523 of 785 ranked configurations on 25 Oct 2026. 381 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

How much does Nemotron 3 Nano Omni 30B A3B cost per 1M tokens?

As of 25 Oct 2026, Nemotron 3 Nano Omni 30B A3B costs $0.400 per 1M input tokens and $1.37 per 1M output tokens, $0.643 blended (three input tokens per output token). The list price last changed on 21 Oct 2026.

When was Nemotron 3 Nano Omni 30B A3B released?

NVIDIA released Nemotron 3 Nano Omni 30B A3B on 29 Apr 2026.

NVIDIAOpen weightsReasoning modelCompare with another model

Nemotron 3 Nano Omni 30B A3B

Nemotron 3 Nano Omni 30B A3B is a NVIDIA open-weights reasoning model, released 29 Apr 2026. Its best configuration (thinking reasoning effort) ranks #523 of 785 on the BenchLeader Index at 45.1 ±6.4, in the lower half. The ± is the point: 381 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in instruction following (63) and lowest in knowledge (36). At $0.643 per million tokens blended it is mid-priced. Output speed of 234 tokens per second puts it in the fastest quarter, with a first answer in 9.3 s. Last measured 29 Apr 2026.

Blended price: $0.643/M; $0.400 in · $1.37 out
Output speed: 234 tok/s; measured by Artificial Analysis
First answer: 9.33 s
Context: 256k
Full answer: 11 s; median, reasoning included
Cost per run: –
Released: 29 Apr 2026

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Overall index45
Reasoning41
Agents & tools41
Knowledge36
Instruction following63
Multimodal36
Long context44
Composite41

How its index has moved

19 Sept 2026 to 21 Oct 2026

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmark	thinking	Source
GPQA Diamond (AA)not in index	46.9%#445	Artificial Analysis
Humanity's Last Exam (AA)not in index	4.8%#469	Artificial Analysis
CritPt	0.0%#315	Artificial Analysis

Coding

Benchmark	thinking	Source
Terminal-Bench 2.1 (AA)not in index	6.7%#199	Artificial Analysis

Agents & tools

Benchmark	thinking	Source
Terminal-Bench Hard	8.3%#235	Artificial Analysis
τ²-Bench Telecom (AA)not in index	45.3%#211	Artificial Analysis
GDPval-AA v2.1not in index	0.0%#124	Artificial Analysis

Knowledge

Benchmark	thinking	Source
AA-Omniscience	-57.4#444	Artificial Analysis
AA-Omniscience: accuracynot in index	15.2%#417	Artificial Analysis
AA-Omniscience: non-hallucinationnot in index	14.3%#348	Artificial Analysis

Instruction following

Benchmark	thinking	Source
IFBench	63.2%#115	Artificial Analysis

Multimodal

Benchmark	thinking	Source
MMMU-Pro	53.2%#232	Artificial Analysis

Long context

Benchmark	thinking	Source
AA-LCR	39.7%#359	Artificial Analysis

Composite

Benchmark	thinking	Source
AA Intelligence Index v4.3.2	10.3#380	Artificial Analysis

Price history

The price above, per 1M tokens, every day it changed.

input outputnow $0.400 in · $1.37 out

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

Workload	Tokens in / out	Cost	With caching	Time
Chat reply	400 / 300	$0.0006	–	10.6 s
Summarize a 30-page report	12,000 / 600	$0.0056	–	11.9 s
Code edit	6,000 / 1,500	$0.0045	–	15.7 s
Agentic coding session	60,000 / 4,000	$0.029	–	26.4 s
Structured extraction	2,000 / 200	$0.0011	–	10.2 s

New this month

Questions people ask

What are Nemotron 3 Nano Omni 30B A3B's benchmark scores?: As of 25 Oct 2026, Nemotron 3 Nano Omni 30B A3B (thinking effort) scores 45.1 ±6.4 on the BenchLeader Index, strongest in instruction following (63) and weakest in knowledge (36). That rests on 7 independent benchmark results, and every score on this page links to its publisher.
How does Nemotron 3 Nano Omni 30B A3B rank?: Nemotron 3 Nano Omni 30B A3B (thinking effort) is #523 of 785 ranked configurations on 25 Oct 2026. 381 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
How much does Nemotron 3 Nano Omni 30B A3B cost per 1M tokens?: As of 25 Oct 2026, Nemotron 3 Nano Omni 30B A3B costs $0.400 per 1M input tokens and $1.37 per 1M output tokens, $0.643 blended (three input tokens per output token). The list price last changed on 21 Oct 2026.
When was Nemotron 3 Nano Omni 30B A3B released?: NVIDIA released Nemotron 3 Nano Omni 30B A3B on 29 Apr 2026.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Nemotron 3 Nano Omni 30B A3B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/nemotron-3-nano-omni-30b-a3b.