Nemotron 3 Super is the stronger all-rounder.
Scores updated · 11 tests both models report · How we compare
Where each one wins
Tests won in each of the three areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Agents and reasoning rest on a single test each.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Nemotron 3 Super pulls ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+35.7points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+31.3points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+29points ahead
Where Nemotron 3 Nano pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 11 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingNemotron 3 Super
- SWE-bench MultilingualNemotron 3 Super by 35.714.149.8+35.7
- Terminal-Bench 2.1Nemotron 3 Super by 31.38.339.6+31.3
- SWE-bench VerifiedNemotron 3 Super by 2934.163.1+29
- SciCodeNemotron 3 Super by 530.135.1+5
Other results5 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- GDPval-AA v2Nemotron 3 Super by 273 rating points473746+273 rating
- PinchBenchNemotron 3 Super by 14.366.180.4+14.3
- HLE (text-only, no tools)Nemotron 3 Super by 9.410.920.3+9.4
- MMLU-ProNemotron 3 Super by 5.478.583.9+5.4
- τ³-Bench BankingNemotron 3 Super by 5.4712.4+5.4
Questions people ask
Which is better, Nemotron 3 Nano or Nemotron 3 Super?
Nemotron 3 Super wins all three areas where both have results: coding, agents and reasoning. Nemotron 3 Nano wins none.
Which is better for coding?
Nemotron 3 Super. It wins 4 of the 4 coding tests both models report; Nemotron 3 Nano wins none.
How do you compare the two?
We use the 11 benchmark tests both models have published scores on. The verdict counts the 6 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 5 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.