Benchmark Almanac

Granite 4.2 3B

Granite 4.2 3B.

IBM Released August 25th, 2026 Family Granite 4.2 The lab's model card Compare with others
3
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
IBM Aug 2026

Granite 4.2 3B

Open weights Small

No Epoch Capabilities Index score yet
AA Intelligence Index 4.7 #63 of 69
  • AgentIF (2026-10 setting) 58.8% #17 /24

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
AgentIF (2026-10 setting) 58.8% #17 of 24 Official leaderboard
LMArena (Elo) 1,289 #248 of 345 Official leaderboard

Other

BenchmarkScoreRankSource
Artificial Analysis Intelligence Index v5 4.7 #63 of 69 Official leaderboard

Who measured it?

Independent runs cover all 3 of its benchmarks.

  • An independent run only 3
Official leaderboards scored it on 3.

Sources: Official leaderboards, Epoch AI (CC BY 4.0) and labs’ model cards