#134 Nemotron 3 Super
none- Cost
- $0.000
- Time
- 137.8s
- Tokens
- 2,447 tok
NVIDIA
Release: 2026-03-11
Tested on: 2026-05-22 00:21
nvidia/nemotron-3-super-120b-a12b::none
120B total (12B active)MoEWeights available
(medium)
(none)
Summary
Nemotron 3 Super scores 5.0 on AI BENCHY and ranks #134. It has 10.0 reliability, a 33.3% pass rate, $0.002 total cost, and 5.66s average response time.
What makes Nemotron 3 Super unique: It stands out most in Domain specific, where it ranks #3, 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
5.0
Consistency
8.7
10.0
$0.002
Total Output Tokens
6,172
Total Input Tokens
0
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 ↑ | Compare | |
| 2026-05-22 00:21 Suite changed | 5.0 | 10.0 | $0.002 | Current run | |
| 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) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-05-22 00:21 · Suite changed | 60/60 attempts | 5.0 | 8.7 | 10.0 | 5/20 | 3 | 6,172 | 0 | $0.002 | 5.66s |
| 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 | — | +0.2 | -0.5 | +0.8 | 0 | +1 | -260 | -63528 | -$0.007 | -381ms |
Benchmark coverage differs: 60/60 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.
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 | 3.4 | 5.8 | |
| 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 |