Granite 4.2 30B vs Nemotron 3 Super 120B A12B
Wins 2 of 6 areas
Agents · Following instructions
Wins 2 of 6 areas
Reasoning · Long documents
The two are evenly matched.Granite 4.2 30B is better at agents and following instructions; Nemotron 3 Super 120B A12B at reasoning and long documents.
Scores updated · 24 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
- Long documentsFinding answers in very long texts01Nemotron 3 Super 120B A12B1 of 1 test
- AgentsCarrying out multi-step tasks on its own20Granite 4.2 30B2 of 3 tests · 1 tie
- Following instructionsDoing exactly what it is asked10Granite 4.2 30B1 of 1 test
- CodingWriting and fixing software22Even2 each
- 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 30B costs 32% less for the same work.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Nemotron 3 Super 120B A12B pulls ahead
- Reasons across sets of long documentsAA-LCR+16.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+15.6points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+14.2points ahead
Where Granite 4.2 30B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+61.4points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+5.7points ahead
- Customer-service tasks in a simulated bankτ-Bench V3 · Banking+4.1points ahead
Every test, side by side
All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingEven
- Terminal-Bench 2.1Nemotron 3 Super 120B A12B by 1226.638.6+12
- SWE-bench MultilingualNemotron 3 Super 120B A12B by 3.941.945.8+3.9
- SWE-bench VerifiedGranite 4.2 30B by 3.35753.7+3.3
- SciCodeGranite 4.2 30B by 1.637.836.2+1.6
AgentsGranite 4.2 30B
- τ-Bench V3 · BankingGranite 4.2 30B by 4.114.410.3+4.1
- GDPValGranite 4.2 30B by 3.83.80+3.8
- Terminal-Bench 4.0tie00tie
ReasoningNemotron 3 Super 120B A12B
- GPQA DiamondNemotron 3 Super 120B A12B by 15.664.480+15.6
- Humanity's Last ExamNemotron 3 Super 120B A12B by 9.611.220.8+9.6
- CritPtNemotron 3 Super 120B A12B by 2.80.33.1+2.8
FactsEven
- AA-Omniscience · Non-hallucinationGranite 4.2 30B by 61.474.413+61.4
- AA-Omniscience · AccuracyNemotron 3 Super 120B A12B by 14.210.124.3+14.2
Long documentsNemotron 3 Super 120B A12B
- AA-LCRNemotron 3 Super 120B A12B by 16.74965.7+16.7
Following instructionsGranite 4.2 30B
- IFBenchGranite 4.2 30B by 5.777.271.5+5.7
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.
- AA-OmniscienceGranite 4.2 30B by 28.6-12.9-41.5+28.6
- AA Agentic IndexGranite 4.2 30B by 9.813.94.1+9.8
- Artificial Analysis Coding IndexNemotron 3 Super 120B A12B by 7.829.937.7+7.8
- MMLU-ProNemotron 3 Super 120B A12B by 6.177.683.7+6.1
- Arena-Hard-V2Nemotron 3 Super 120B A12B by 667.973.9+6
- HMMT 2025Nemotron 3 Super 120B A12B by 5.589.294.7+5.5
- IFBench (prompt)Granite 4.2 30B by 3.877.273.4+3.8
- AIME25 no toolsNemotron 3 Super 120B A12B by 389.292.2+3
- AIME 2025Nemotron 3 Super 120B A12B by 189.290.2+1
- AA Intelligencetie12.712.8tie
Questions people ask
Which is better, Granite 4.2 30B or Nemotron 3 Super 120B A12B?
Granite 4.2 30B and Nemotron 3 Super 120B A12B each win two of the six areas where both have results. Granite 4.2 30B wins agents and following instructions; Nemotron 3 Super 120B A12B wins reasoning and long documents. Granite 4.2 30B costs 32% less. They are level on coding and facts.
Which is better for coding?
Neither. They win 2 coding tests each of the 4 both models report.
Which is cheaper?
Granite 4.2 30B costs $0.16 per million input tokens and $0.65 per million output tokens; Nemotron 3 Super 120B A12B costs $0.30 and $0.90. That makes Granite 4.2 30B about 32% cheaper for the same work.
How do you compare the two?
We use the 24 benchmark tests both models have published scores on. The verdict counts the 14 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.