Granite 4.2 30B vs Granite 4.2 8B
Wins 4 of 6 areas
Coding · Agents · Reasoning · Long documents
Wins 1 of 6 areas
Following instructions
Granite 4.2 30B is the stronger all-rounder.Granite 4.2 8B is cheaper and better at following instructions.
Scores updated · 33 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.
- CodingWriting and fixing software60Granite 4.2 30B6 of 6 tests
- AgentsCarrying out multi-step tasks on its own20Granite 4.2 30B2 of 3 tests · 1 tie
- ReasoningHard problems that need careful thinking20Granite 4.2 30B2 of 3 tests · 1 tie
- Long documentsFinding answers in very long texts10Granite 4.2 30B1 of 1 test
- Following instructionsDoing exactly what it is asked01Granite 4.2 8B1 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 8B costs 62% 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 Granite 4.2 30B pulls ahead
- Long, multi-file coding tasks in real codebasesSWE-bench Pro+14.2points ahead
- Fixes real GitHub issues in many programming languagesSWE-bench Multilingual+11.1points ahead
- Fixes real GitHub issues in Python projectsSWE-bench Verified+9.3points ahead
Where Granite 4.2 8B pulls ahead
- Follows unfamiliar, precisely checkable instructionsIFBench+2.1points ahead
- Answers hard knowledge questions correctlyAA-Omniscience · Accuracy+1.1points ahead
Every test, side by side
All 33 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGranite 4.2 30B
- SWE-bench ProGranite 4.2 30B by 14.233.319.1+14.2
- SWE-bench MultilingualGranite 4.2 30B by 11.141.930.8+11.1
- SWE-bench VerifiedGranite 4.2 30B by 9.35747.7+9.3
- Terminal-Bench 2.1Granite 4.2 30B by 8.226.618.4+8.2
- SciCodeGranite 4.2 30B by 6.337.831.5+6.3
- LiveCodeBench v6Granite 4.2 30B by 2.675.873.2+2.6
AgentsGranite 4.2 30B
- τ-Bench V3 · BankingGranite 4.2 30B by 6.814.47.6+6.8
- GDPValGranite 4.2 30B by 3.83.80+3.8
- Terminal-Bench 4.0tie00tie
ReasoningGranite 4.2 30B
- Humanity's Last ExamGranite 4.2 30B by 1.511.29.7+1.5
- GPQA DiamondGranite 4.2 30B by 1.364.463.1+1.3
- CritPttie0.30.3tie
FactsEven
- AA-Omniscience · Non-hallucinationGranite 4.2 30B by 6.474.468+6.4
- AA-Omniscience · AccuracyGranite 4.2 8B by 1.110.111.2+1.1
Following instructionsGranite 4.2 8B
- IFBenchGranite 4.2 8B by 2.177.279.3+2.1
Other results17 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.
- BFCLv4Granite 4.2 30B by 11.161.450.3+11.1
- HMMT 2025Granite 4.2 30B by 10.989.278.3+10.9
- HMMT Feb25Granite 4.2 30B by 10.989.278.3+10.9
- AA Agentic IndexGranite 4.2 30B by 10.213.93.7+10.2
- RULER 128KGranite 4.2 30B by 1081.471.4+10
- RULER 64KGranite 4.2 30B by 99081+9
- Artificial Analysis Coding IndexGranite 4.2 30B by 7.529.922.4+7.5
- MMLU-ProX lite (IBM)Granite 4.2 30B by 5.566.661.1+5.5
- AA-OmniscienceGranite 4.2 30B by 4.3-12.9-17.2+4.3
- τ³-BenchGranite 4.2 30B by 3.96258.1+3.9
- MMLU-ProGranite 4.2 30B by 3.677.674+3.6
- Arena-Hard-V2Granite 4.2 30B by 2.767.965.2+2.7
- AIME 2025Granite 4.2 30B by 2.589.286.7+2.5
- AIME25 no toolsGranite 4.2 30B by 2.589.286.7+2.5
- IFBench (prompt)Granite 4.2 8B by 2.177.279.3+2.1
- AA IntelligenceGranite 4.2 30B by 1.612.711.1+1.6
- BirdBenchtie41.941.1tie
Questions people ask
Which is better, Granite 4.2 30B or Granite 4.2 8B?
Granite 4.2 30B wins four of the six areas where both have results: coding, agents, reasoning and long documents. Granite 4.2 8B wins following instructions, and costs 62% less. They are level on facts.
Which is better for coding?
Granite 4.2 30B. It wins 6 of the 6 coding tests both models report; Granite 4.2 8B wins none.
Which is cheaper?
Granite 4.2 30B costs $0.16 per million input tokens and $0.65 per million output tokens; Granite 4.2 8B costs $0.06 and $0.25. That makes Granite 4.2 8B about 62% cheaper for the same work.
How do you compare the two?
We use the 33 benchmark tests both models have published scores on. The verdict counts the 16 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 17 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.