NVIDIA
Release: 2026-04-28
Tested on: 2026-05-08 15:30
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning::medium
30B total (3B active)MoEWeights available
(medium)
(default)
Summary
Nemotron 3 Nano Omni 30b A3b Reasoning scores 2.7 on AI BENCHY and ranks #432. It has 10.0 reliability, a 26.1% pass rate, $0.000 total cost, and 17.13s average response time.
What makes Nemotron 3 Nano Omni 30b A3b Reasoning unique: It stands out most in Anti-AI Tricks, where it ranks #1, while Coding is its weakest area at #13. Its total benchmark cost is unusually low for its score range. It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.
Archived model: this model is no longer updated or tested on new tests.
Model facts
Researched on 2026-08-12
- Parameters
- 30B total (3B active)
- Architecture
- MoE
- Availability
- Weights available
- License
- NVIDIA Open Model
2.7
Consistency
6.4
10.0
$0.000
Total Output Tokens
206,534
Total Input Tokens
11,661
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.
Flaky tests
5
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-05-08 15:30 Suite changed | 2.7 | 10.0 | $0.000 | Current run | |
| 2026-04-28 23:26 First recorded run | 5.2 | 10.0 | $0.000 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-05-08 15:30 · Current run | 57/69 attempts | 2.7 | 6.4 | 10.0 | 4/19 | 5 | 206,534 | 11,661 | $0.000 | 17.13s |
| 2026-04-28 23:26 · First recorded run | 54/54 attempts | 5.2 | 5.9 | 10.0 | 4/16 | 8 | 235,283 | 0 | $0.000 | 14.46s |
| Difference | — | -2.5 | +0.5 | 0.0 | -2 | -3 | -28749 | +11661 | $0.000 | +2668ms |
Benchmark coverage differs: 57/69 attempts (Target: 3 repeats per test) versus 54/54 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.
These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.
Price History
Historical pricing data for this model from OpenRouter.
| Date | Input Price | Output Price | Cache Read Price | Cache Write Price |
|---|---|---|---|---|
| 2026-06-04 15:40 | $0.000 / 1M | $0.000 / 1M | N/A | N/A |
Charts
Choose the first model, then click a second model to open a side-by-side page.
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 0.0 | 0.0 | |
| Anti-AI Tricks | 6.4 | 7.9 | |
| Coding | 1.1 | 0.6 | |
| Combined | 1.5 | 5.0 | |
| Data parsing and extraction | 7.3 | 5.9 | |
| Domain specific | 2.9 | 7.2 | |
| General Intelligence | 3.0 | 10.0 | |
| Instructions following | 7.3 | 10.0 | |
| Puzzle Solving | 2.9 | 7.2 | |
| Tool Calling | 3.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |