Advertise here
#129

Nemotron 3 Nano Omni 30b A3b Reasoning

NVIDIA Release: 2026-04-28 Tested on: 2026-04-28 23:08 nvidia/nemotron-3-nano-omni-30b-a3b-reasoning::none
30B total (3B active)MoEWeights available
(medium) (default)

Summary

Nemotron 3 Nano Omni 30b A3b Reasoning scores 4.4 on AI BENCHY and ranks #129. It has 10.0 reliability, a 25.0% pass rate, $0.000 total cost, and 698ms average response time.

What makes Nemotron 3 Nano Omni 30b A3b Reasoning unique: It stands out most in Coding, where it ranks #1, while Anti-AI Tricks is its weakest area at #18. Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.

Archived model: this model is no longer updated or tested on new tests.

Model facts

Researched on 2026-08-12

Reported
Parameters
30B total (3B active)
Architecture
MoE
Availability
Weights available
License
NVIDIA Open Model
Parameter source Availability source

Score

4.4

Consistency

8.4

Reliability

10.0

Total Cost (Current Price)

$0.000

Total Output Tokens

1,567

Total Input Tokens

0

Input Price

$0.000 / 1M

Output Price

$0.000 / 1M

Cache Read Price

N/A

Cache Write Price

N/A

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 14

Attempt pass rate: 25.0%

Flaky tests

3

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

698ms

Response Time (max): 2.21s

Response Time (total): 11.17s

Wrong answer: 11 Did not follow instructions: 3

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-05-08 15:30 Suite changed 3.2 10.0 $0.000 Compare
2026-04-28 23:08 First recorded run 4.4 10.0 $0.000 Current run

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 5.2 7.9
Coding 10.0 10.0
Combined 0.0 0.0
Data parsing and extraction 3.8 5.8
Domain specific 3.6 7.2
General Intelligence 3.6 9.7
Instructions following 4.6 10.0
Puzzle Solving 3.0 10.0
Tool Calling 0.0 0.0

Compared models