#139 Nemotron 3 Super
none- Cost
- $0.000
- Time
- 137.8s
- Tokens
- 2,447 tok
NVIDIA
Release: 2026-03-11
Tested on: 2026-06-04 13:53
nvidia/nemotron-3-super-120b-a12b::none
120B total (12B active)MoEWeights available
(medium)
(none)
Summary
Nemotron 3 Super scores 4.9 on AI BENCHY and ranks #139. It has 10.0 reliability, a 31.8% pass rate, $0.007 total cost, and 5.30s average response time.
What makes Nemotron 3 Super unique: It stands out most in Domain specific, where it ranks #4, while Anti-AI Tricks is its weakest area at #18. Its total benchmark cost is unusually low for its score range.
Model facts
Researched on 2026-08-12
- Parameters
- 120B total (12B active)
- Architecture
- MoE
- Availability
- Weights available
- License
- NVIDIA Open Model
4.9
Consistency
8.8
10.0
Total Output Tokens
6,195
Total Input Tokens
36,456
Input Price
$0.090 / 1M
Output Price
$0.450 / 1M
Flaky tests
3
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-08-14 02:35 Re-test | 4.8 | 9.2 | $0.008 ↑ | Compare | |
| 2026-07-16 22:47 New test added | 4.9 | 8.5 | $0.017 ↑ | Compare | |
| 2026-06-04 13:53 New test added | 4.9 | 10.0 | $0.007 ↑ | Current run | |
| 2026-05-22 00:21 Suite changed | 5.0 | 10.0 | $0.002 | Compare | |
| 2026-05-08 15:31 Suite changed | 5.2 | 10.0 | $0.002 | Compare | |
| 2026-04-20 17:48 First recorded run | 5.1 | N/A | $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) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-06-04 13:53 · New test added | 63/63 attempts | 4.9 | 8.8 | 10.0 | 5/21 | 3 | 6,195 | 36,456 | $0.007 | 5.30s |
| 2026-08-14 02:35 · Re-test | 66/66 attempts | 4.8 | 9.2 | 9.2 | 5/22 | 2 | 6,432 | 63,528 | $0.008 | 6.04s |
| Difference | — | +0.1 | -0.4 | +0.8 | 0 | +1 | -237 | -27072 | -$0.002 | -743ms |
Benchmark coverage differs: 63/63 attempts (Target: 3 repeats per test) versus 66/66 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 |
|---|---|---|
| 2026-06-04 14:42 | $0.090 / 1M | $0.450 / 1M |
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Nemotron 3 SupernoneFree AvailablevsLing-2.6-flashnoneNemotron 3 SupernoneFree AvailablevsHy4 previewnoneNemotron 3 SupernoneFree AvailablevsMercury 2.5 PreviewnoneNemotron 3 SupernoneFree AvailablevsRing-2.6-1TnoneNemotron 3 SupernoneFree AvailablevsGPT-4o-mininoneNemotron 3 SupernoneFree AvailablevsNemotron 3.5 LightninglowFree AvailableNemotron 3 SupernoneFree AvailablevsDeepSeek V3.2noneNemotron 3 SupernoneFree AvailablevsGPT-5.4 NanononeNemotron 3 SupernoneFree AvailablevsLaguna S 2.1lowFree AvailableNemotron 3 SupernoneFree AvailablevsTrinity Large Thinkinghigh
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 4.8 | 10.0 | |
| Coding | 3.3 | 7.2 | |
| Combined | 3.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 3.6 | 7.2 | |
| General Intelligence | 4.6 | 10.0 | |
| Instructions following | 6.3 | 10.0 | |
| Puzzle Solving | 5.5 | 10.0 | |
| Tool Calling | 4.7 | 1.6 | |
| Trivia | 3.0 | 10.0 |