Granite 4.2 3B vs Nemotron 3 Super 120B A12B
Wins 1 of 6 areas
Following instructions
Wins 4 of 6 areas
Coding · Agents · Reasoning · Long documents
Nemotron 3 Super 120B A12B is the stronger all-rounder.Granite 4.2 3B is cheaper and better at following instructions.
Scores updated · 21 tests both models report · How we compare
Where each one wins
Tests won in each of the six 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.
- ReasoningHard problems that need careful thinking03Nemotron 3 Super 120B A12B3 of 3 tests
- CodingWriting and fixing software02Nemotron 3 Super 120B A12B2 of 2 tests
- AgentsCarrying out multi-step tasks on its own01Nemotron 3 Super 120B A12B1 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts01Nemotron 3 Super 120B A12B1 of 1 test
- Following instructionsDoing exactly what it is asked10Granite 4.2 3B1 of 1 test
- FactsGetting facts right instead of making them up11Even1 each
Long documents and following instructions rest on a single test each.
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.
Granite 4.2 3B costs 88% less for the same work.
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
- Reasons across sets of long documentsAA-LCR+41.4points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+24.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+24.1points ahead
Where Granite 4.2 3B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+60.7points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+2.8points ahead
Every test, side by side
All 21 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingNemotron 3 Super 120B A12B
- Terminal-Bench 2.1Nemotron 3 Super 120B A12B by 24.713.938.6+24.7
- SciCodeNemotron 3 Super 120B A12B by 10.925.336.2+10.9
AgentsNemotron 3 Super 120B A12B
- τ-Bench V3 · BankingNemotron 3 Super 120B A12B by 4.75.610.3+4.7
- GDPValtie00tie
- Terminal-Bench 4.0tie00tie
ReasoningNemotron 3 Super 120B A12B
- GPQA DiamondNemotron 3 Super 120B A12B by 24.155.980+24.1
- Humanity's Last ExamNemotron 3 Super 120B A12B by 14.26.620.8+14.2
- CritPtNemotron 3 Super 120B A12B by 3.103.1+3.1
FactsEven
- AA-Omniscience · Non-hallucinationGranite 4.2 3B by 60.773.713+60.7
- AA-Omniscience · AccuracyNemotron 3 Super 120B A12B by 15.19.224.3+15.1
Long documentsNemotron 3 Super 120B A12B
- AA-LCRNemotron 3 Super 120B A12B by 41.424.365.7+41.4
Following instructionsGranite 4.2 3B
- IFBenchGranite 4.2 3B by 2.874.371.5+2.8
Other results9 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.
- Arena-Hard-V2Nemotron 3 Super 120B A12B by 38.93573.9+38.9
- HMMT 2025Nemotron 3 Super 120B A12B by 2866.794.7+28
- AA-OmniscienceGranite 4.2 3B by 26.8-14.7-41.5+26.8
- Artificial Analysis Coding IndexNemotron 3 Super 120B A12B by 20.217.537.7+20.2
- MMLU-ProNemotron 3 Super 120B A12B by 15.967.883.7+15.9
- AIME25 no toolsNemotron 3 Super 120B A12B by 13.978.392.2+13.9
- AIME 2025Nemotron 3 Super 120B A12B by 11.978.390.2+11.9
- AA IntelligenceNemotron 3 Super 120B A12B by 3.79.112.8+3.7
- IFBench (prompt)tie74.373.4tie
Questions people ask
Which is better, Granite 4.2 3B or Nemotron 3 Super 120B A12B?
Nemotron 3 Super 120B A12B wins four of the six areas where both have results: coding, agents, reasoning and long documents. Granite 4.2 3B wins following instructions, and costs 88% less. They are level on facts.
Which is better for coding?
Nemotron 3 Super 120B A12B. It wins 2 of the 2 coding tests both models report; Granite 4.2 3B wins none.
Which is cheaper?
Granite 4.2 3B costs $0.03 per million input tokens and $0.12 per million output tokens; Nemotron 3 Super 120B A12B costs $0.30 and $0.90. That makes Granite 4.2 3B about 88% cheaper for the same work.
How do you compare the two?
We use the 21 benchmark tests both models have published scores on. The verdict counts the 12 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 9 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.