Model comparison
Granite 4.1 8b vs Granite 4.2 3b
Granite 4.2 3b is the stronger model overall, scoring 39.0 to 36.8 on the Noometry Index.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. Granite 4.1 8b scores higher in 1 category and Granite 4.2 3b in 6 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Granite 4.2 3b leads 39.4 to 29.9.
Side by side
| Granite 4.1 8b | Granite 4.2 3b | |
|---|---|---|
| Provider | IBM | IBM |
| Noometry Index | 36.8 | 39.0 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 3b leads
Granite 4.1 8b: 29.9 (#291), Granite 4.2 3b: 39.4 (#146)
| Benchmark | Granite 4.1 8b | Granite 4.2 3b |
|---|---|---|
| LMArena Coding | 1313 | 1363 |
| LMArena WebDev | 1190 | — |
Reasoning Too close to call
Granite 4.1 8b: 24.6 (#142), Granite 4.2 3b: 25.0 (#136)
| Benchmark | Granite 4.1 8b | Granite 4.2 3b |
|---|---|---|
| LMArena Hard Prompts | 1294 | 1308 |
Math Not comparable
Granite 4.1 8b: 33.8 (#167), Granite 4.2 3b: —
| Benchmark | Granite 4.1 8b | Granite 4.2 3b |
|---|---|---|
| LMArena Math | 1311 | — |
Knowledge Too close to call
Granite 4.1 8b: 35.5 (#171), Granite 4.2 3b: 35.6 (#169)
| Benchmark | Granite 4.1 8b | Granite 4.2 3b |
|---|---|---|
| LMArena Expert | 1310 | 1313 |
Multilingual Too close to call
Granite 4.1 8b: 41.8 (#199), Granite 4.2 3b: 42.4 (#193)
| Benchmark | Granite 4.1 8b | Granite 4.2 3b |
|---|---|---|
| LMArena Non-English | 1261 | 1268 |
| LMArena Chinese | 1335 | 1268 |
| LMArena Russian | 1238 | 1249 |
Instruction Following Too close to call
Granite 4.1 8b: 67.0 (#198), Granite 4.2 3b: 67.2 (#195)
| Benchmark | Granite 4.1 8b | Granite 4.2 3b |
|---|---|---|
| LMArena Instruction Following | 1268 | 1271 |
Long Context Too close to call
Granite 4.1 8b: 38.7 (#188), Granite 4.2 3b: 39.3 (#179)
| Benchmark | Granite 4.1 8b | Granite 4.2 3b |
|---|---|---|
| LMArena Longer Query | 1275 | 1293 |
Writing & Preference Too close to call
Granite 4.1 8b: 48.3 (#199), Granite 4.2 3b: 47.9 (#202)
| Benchmark | Granite 4.1 8b | Granite 4.2 3b |
|---|---|---|
| LMArena Text | 1291 | 1295 |
| LMArena Creative Writing | 1249 | 1215 |
| LMArena Multi-Turn | 1269 | 1293 |
Frequently asked questions
Is Granite 4.1 8b better than Granite 4.2 3b?
Granite 4.2 3b is the stronger model overall, scoring 39.0 to 36.8 on the Noometry Index.
Is Granite 4.1 8b or Granite 4.2 3b better for coding?
Granite 4.2 3b scores higher on coding benchmarks: 39.4 versus 29.9 in the Noometry coding category.
How many benchmarks do Granite 4.1 8b and Granite 4.2 3b share?
11 benchmarks have published results for both models. Granite 4.1 8b has 13 scored results on Noometry and Granite 4.2 3b has 11.