#36
NVIDIA · Release: 2026-03-11 · nvidia/nemotron-3-super-120b-a12b::medium
Flaky tests
3
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Charts
Choose the first model, then click a second model to open a side-by-side page.
Avg Score vs Total Cost
Response Time (avg)
Avg Score vs Response Time (avg)
Total Output Tokens
Avg Score vs Total Output Tokens
Quick Compare
Nemotron 3 Super 120b A12bmediumFree AvailablevsGPT-5 MinimediumNemotron 3 Super 120b A12bmediumFree AvailablevsGLM 5noneNemotron 3 Super 120b A12bmediumFree AvailablevsDeepSeek V3.2noneNemotron 3 Super 120b A12bmediumFree AvailablevsGrok 4.1 FastmediumNemotron 3 Super 120b A12bmediumFree AvailablevsGPT-5 NanomediumNemotron 3 Super 120b A12bmediumFree AvailablevsGemini 3 Flash PreviewmediumNemotron 3 Super 120b A12bmediumFree AvailablevsGemini 3.1 Pro PreviewmediumNemotron 3 Super 120b A12bmediumFree AvailablevsStep 3.5 FlashmediumFree Available
Category Breakdown
| Category | Avg Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 10.0 | 10.0 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 9.9 | 10.0 | |
| Domain specific | 10.0 | 4.4 | |
| General Intelligence | 2.0 | 9.9 | |
| Instructions following | 7.0 | 6.5 | |
| Puzzle Solving | 1.3 | 9.8 | |
| Tool Calling | 10.0 | 10.0 |