Gemma 4 26B A4B vs NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16
Wins 1 of 1 area
Reasoning
Wins 0 of 1 area
—
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+13points ahead
Where NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16 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.
- Minerva MathNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16 by 4443.787.7+44
- HumanEvalNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16 by 31.35081.3+31.3
- MATH-500 (EM)Gemma 4 26B A4B by 14.195.781.6+14.1
- SuperGPQAGemma 4 26B A4B by 13.761.447.6+13.7
- MMLUNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16 by 6.377.884.1+6.3
- MMLU-ProGemma 4 26B A4B by 6.382.676.3+6.3
- HellaSwagNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16 by 3.785.389+3.7
- ARC-ChallengeNVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16 by 3.292.896+3.2
- OpenBookQAtie48.848.8tie
- WinoGrandetie79.179.1tie
Questions people ask
Which is better, Gemma 4 26B A4B or NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16?
Gemma 4 26B A4B wins the one area where both have results: reasoning. NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-Base-BF16 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.