AI BENCHY
Your ad here

#107

Nemotron 3 Nano Omni 30b A3b Reasoning

NVIDIA Release: 2026-04-28 Tested on: 2026-04-28 23:26 nvidia/nemotron-3-nano-omni-30b-a3b-reasoning::medium
(medium) (none)

Score

5.2

Consistency

5.9

Reliability

10.0

Total Cost

$0.000

Total Output Tokens

235,283

Input Price

$0.000 / 1M

Output Price

$0.000 / 1M

Tests Correct

Wrong Tests: 12

Attempt pass rate: 47.9%

Flaky tests

8

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

Response Time (avg)

14.46s

Response Time (max): 147.45s

Response Time (total): 231.37s

Wrong answer: 8 Did not follow instructions: 3 No answer: 1

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

Quick Compare

Nemotron 3 Nano Omni 30b A3b ReasoningmediumFree AvailablevsGLM 5 TurbononeNemotron 3 Nano Omni 30b A3b ReasoningmediumFree AvailablevsTrinity Large PreviewnoneNemotron 3 Nano Omni 30b A3b ReasoningmediumFree AvailablevsKimi K2.5noneNemotron 3 Nano Omni 30b A3b ReasoningmediumFree AvailablevsDeepSeek V4 FlashnoneNemotron 3 Nano Omni 30b A3b ReasoningmediumFree AvailablevsGLM 5.1noneNemotron 3 Nano Omni 30b A3b ReasoningmediumFree AvailablevsGemini 3 Flash PreviewmediumNemotron 3 Nano Omni 30b A3b ReasoningmediumFree AvailablevsGemini 3.1 Pro PreviewmediumNemotron 3 Nano Omni 30b A3b ReasoningmediumFree AvailablevsHY3 PreviewhighFree Available

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 7.0 5.9
Coding 3.3 1.7
Combined 0.0 0.0
Data parsing and extraction 7.3 5.9
Domain specific 2.9 7.2
General Intelligence 4.8 9.9
Instructions following 6.9 6.3
Puzzle Solving 3.5 4.4
Tool Calling 0.0 0.0

Compared models