Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

Nemotron 3 Super 120B A12B vs NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16

NVIDIA · released

Wins 1 of 1 area

Reasoning

NVIDIA · released

Wins 0 of 1 area

—

Nemotron 3 Super 120B A12B is the stronger all-rounder.

Scores updated · 22 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.

Nemotron 3 Super 120B A12B$0.30 to read · $0.90 to write$1.20Price from Artificial Analysis
NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16No current price is tracked.

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 120B A12B pulls ahead

  • Very hard expert questions across many subjectsHumanity's Last Exam+4.3points aheadNemotron 3 Super 120B A12B20.8NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF1616.5

Where NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16 pulls ahead

No clear win on a test scored out of 100.

Every test, side by side

All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.

ReasoningNemotron 3 Super 120B A12B

Full reasoning ranking

Other results21 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.

Questions people ask

Which is better, Nemotron 3 Super 120B A12B or NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16?

Nemotron 3 Super 120B A12B wins the one area where both have results: reasoning. NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-BF16 wins none.

How do you compare the two?

We use the 22 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 21 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.