Granite 4.2 3B vs Qwen3.5 9B
Wins 1 of 6 areas
Following instructions
Wins 4 of 6 areas
Coding · Agents · Reasoning · Long documents
Qwen3.5 9B is the stronger all-rounder.Granite 4.2 3B is 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 thinking02Qwen3.5 9B2 of 3 tests · 1 tie
- CodingWriting and fixing software12Qwen3.5 9B2 of 3 tests
- AgentsCarrying out multi-step tasks on its own01Qwen3.5 9B1 of 3 tests · 2 ties
- Long documentsFinding answers in very long texts01Qwen3.5 9B1 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.
The biggest differences
The three tests each model wins by the widest margin. Scores are out of 100.
Where Qwen3.5 9B pulls ahead
- Reasons across sets of long documentsAA-LCR+45.7points ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+24.7points ahead
- Command-line tasks in a real terminalTerminal-Bench 2.1+15.3points ahead
Where Granite 4.2 3B pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+57.3points ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+7.6points ahead
- Recent programming contest problemsLiveCodeBench v6+4.1points 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.
CodingQwen3.5 9B
- Terminal-Bench 2.1Qwen3.5 9B by 15.313.929.2+15.3
- SciCodeQwen3.5 9B by 4.225.329.5+4.2
- LiveCodeBench v6Granite 4.2 3B by 4.169.765.6+4.1
AgentsQwen3.5 9B
- τ-Bench V3 · BankingQwen3.5 9B by 1.45.67+1.4
- Terminal-Bench 4.0tie00.5tie
- GDPValtie00tie
ReasoningQwen3.5 9B
- GPQA DiamondQwen3.5 9B by 24.755.980.6+24.7
- Humanity's Last ExamQwen3.5 9B by 8.36.614.9+8.3
- CritPttie00.3tie
FactsEven
- AA-Omniscience · Non-hallucinationGranite 4.2 3B by 57.373.716.4+57.3
- AA-Omniscience · AccuracyQwen3.5 9B by 7.29.216.4+7.2
Following instructionsGranite 4.2 3B
- IFBenchGranite 4.2 3B by 7.674.366.7+7.6
Other results8 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 3B by 38.8-14.7-53.5+38.8
- RULER 128KQwen3.5 9B by 31.855.387.1+31.8
- AIME25 no toolsGranite 4.2 3B by 22.278.356.1+22.2
- HMMT 2025Qwen3.5 9B by 16.266.782.9+16.2
- MMLU-ProQwen3.5 9B by 14.767.882.5+14.7
- BFCLv4Qwen3.5 9B by 13.752.466.1+13.7
- Artificial Analysis Coding IndexQwen3.5 9B by 11.217.528.7+11.2
- AA IntelligenceQwen3.5 9B by 2.19.111.2+2.1
Questions people ask
Which is better, Granite 4.2 3B or Qwen3.5 9B?
Qwen3.5 9B wins four of the six areas where both have results: coding, agents, reasoning and long documents. Granite 4.2 3B wins following instructions. They are level on facts.
Which is better for coding?
Qwen3.5 9B. It wins 2 of the 3 coding tests both models report; Granite 4.2 3B wins 1.
How do you compare the two?
We use the 21 benchmark tests both models have published scores on. The verdict counts the 13 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 8 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.