Model comparison
Granite 4.2 3b vs Granite 4.0 H Small
Granite 4.2 3b is the stronger model overall, scoring 39.0 to 35.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. Granite 4.2 3b scores higher in 6 categories and Granite 4.0 H Small in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.2 3b leads 35.6 to 31.5.
Side by side
| Granite 4.2 3b | Granite 4.0 H Small | |
|---|---|---|
| Provider | IBM | IBM |
| Noometry Index | 39.0 | 35.9 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 11 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 3b leads
Granite 4.2 3b: 39.4 (#146), Granite 4.0 H Small: 35.8 (#207)
| Benchmark | Granite 4.2 3b | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | 1363 | 1247 |
Reasoning Granite 4.2 3b leads
Granite 4.2 3b: 25.0 (#136), Granite 4.0 H Small: 23.4 (#164)
| Benchmark | Granite 4.2 3b | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | 1308 | 1240 |
Math Not comparable
Granite 4.2 3b: —, Granite 4.0 H Small: 29.3 (#219)
| Benchmark | Granite 4.2 3b | Granite 4.0 H Small |
|---|---|---|
| Omni-MATH | — | 29.6% |
| LMArena Math | — | 1251 |
Knowledge Granite 4.2 3b leads
Granite 4.2 3b: 35.6 (#169), Granite 4.0 H Small: 31.5 (#210)
| Benchmark | Granite 4.2 3b | Granite 4.0 H Small |
|---|---|---|
| LMArena Expert | 1313 | 1244 |
| MMLU-Pro | — | 56.9% |
| Vectara Hallucination Rate | — | 5.2% |
| GPQA (HELM) | — | 38.3% |
Multilingual Granite 4.2 3b leads
Granite 4.2 3b: 42.4 (#193), Granite 4.0 H Small: 38.7 (#223)
| Benchmark | Granite 4.2 3b | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | 1268 | 1216 |
| LMArena Chinese | 1268 | 1250 |
| LMArena Russian | 1249 | 1198 |
| LMArena Spanish | — | 1258 |
Instruction Following Granite 4.0 H Small leads
Granite 4.2 3b: 67.2 (#195), Granite 4.0 H Small: 68.9 (#178)
| Benchmark | Granite 4.2 3b | Granite 4.0 H Small |
|---|---|---|
| LMArena Instruction Following | 1271 | 1221 |
| IFEval | — | 89% |
Long Context Granite 4.2 3b leads
Granite 4.2 3b: 39.3 (#179), Granite 4.0 H Small: 37.6 (#209)
| Benchmark | Granite 4.2 3b | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | 1293 | 1240 |
Writing & Preference Granite 4.2 3b leads
Granite 4.2 3b: 47.9 (#202), Granite 4.0 H Small: 44.0 (#222)
| Benchmark | Granite 4.2 3b | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | 1295 | 1241 |
| LMArena Creative Writing | 1215 | 1210 |
| LMArena Multi-Turn | 1293 | 1243 |
| WildBench | — | 73.9% |
Frequently asked questions
Is Granite 4.2 3b better than Granite 4.0 H Small?
Granite 4.2 3b is the stronger model overall, scoring 39.0 to 35.9 on the Noometry Index.
Is Granite 4.2 3b or Granite 4.0 H Small better for coding?
Granite 4.2 3b scores higher on coding benchmarks: 39.4 versus 35.8 in the Noometry coding category.
How many benchmarks do Granite 4.2 3b and Granite 4.0 H Small share?
11 benchmarks have published results for both models. Granite 4.2 3b has 11 scored results on Noometry and Granite 4.0 H Small has 19.