Gemma 4 26B A4B 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 one area 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.
Reasoning rests on a single test.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Gemma 4 26B A4B pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+29.2points ahead
Where Nemotron 3 Ultra 550B A55B Base 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.
Other results10 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.
- HumanEvalNemotron 3 Ultra 550B A55B Base by 33.85083.8+33.8
- GPQA (unspecified)Gemma 4 26B A4B by 32.382.350+32.3
- MMLUNemotron 3 Ultra 550B A55B Base by 11.377.889.1+11.3
- HellaSwagNemotron 3 Ultra 550B A55B Base by 5.285.390.5+5.2
- ARC-ChallengeNemotron 3 Ultra 550B A55B Base by 4.692.897.3+4.6
- RULER 1MNemotron 3 Ultra 550B A55B Base by 3.972.976.8+3.9
- MMLU-ProGemma 4 26B A4B by 3.582.679.1+3.5
- RULER 256Ktie85.786.2tie
- OpenBookQAtie48.848.6tie
- WinoGrandetie79.179.3tie
Questions people ask
Which is better, Gemma 4 26B A4B or Nemotron 3 Ultra 550B A55B Base?
Gemma 4 26B A4B wins the one area where both have results: reasoning. Nemotron 3 Ultra 550B A55B Base wins none.
How do you compare the two?
We use the 11 benchmark tests both models have published scores on. The verdict counts the 1 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 10 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.