Model comparison
Granite 3.1 2b Instruct vs Granite 4.0 H Small
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 32.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Granite 3.1 2b Instruct scores higher in 1 category and Granite 4.0 H Small in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Granite 4.0 H Small leads 68.9 to 58.0.
Side by side
| Granite 3.1 2b Instruct | Granite 4.0 H Small | |
|---|---|---|
| Provider | IBM | IBM |
| Noometry Index | 32.6 | 35.9 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 12 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.0 H Small leads
Granite 3.1 2b Instruct: 32.9 (#255), Granite 4.0 H Small: 35.8 (#207)
| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | 1149 | 1247 |
Reasoning Granite 4.0 H Small leads
Granite 3.1 2b Instruct: 21.0 (#206), Granite 4.0 H Small: 23.4 (#164)
| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1240 |
Math Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 30.6 (#206), Granite 4.0 H Small: 29.3 (#219)
| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Math | 1159 | 1251 |
| Omni-MATH | — | 29.6% |
Knowledge Granite 4.0 H Small leads
Granite 3.1 2b Instruct: 30.3 (#223), Granite 4.0 H Small: 31.5 (#210)
| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Expert | 1131 | 1244 |
| MMLU-Pro | — | 56.9% |
| Vectara Hallucination Rate | — | 5.2% |
| GPQA (HELM) | — | 38.3% |
Multilingual Granite 4.0 H Small leads
Granite 3.1 2b Instruct: 29.2 (#264), Granite 4.0 H Small: 38.7 (#223)
| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | 1068 | 1216 |
| LMArena Chinese | 1138 | 1250 |
| LMArena Russian | 1063 | 1198 |
| LMArena Spanish | — | 1258 |
Instruction Following Granite 4.0 H Small leads
Granite 3.1 2b Instruct: 58.0 (#259), Granite 4.0 H Small: 68.9 (#178)
| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Instruction Following | 1116 | 1221 |
| IFEval | — | 89% |
Long Context Granite 4.0 H Small leads
Granite 3.1 2b Instruct: 35.0 (#239), Granite 4.0 H Small: 37.6 (#209)
| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | 1155 | 1240 |
Writing & Preference Granite 4.0 H Small leads
Granite 3.1 2b Instruct: 34.3 (#269), Granite 4.0 H Small: 44.0 (#222)
| Benchmark | Granite 3.1 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | 1127 | 1241 |
| LMArena Creative Writing | 1116 | 1210 |
| LMArena Multi-Turn | 1099 | 1243 |
| WildBench | — | 73.9% |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Granite 4.0 H Small?
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 32.6 on the Noometry Index.
Is Granite 3.1 2b Instruct or Granite 4.0 H Small better for coding?
Granite 4.0 H Small scores higher on coding benchmarks: 35.8 versus 32.9 in the Noometry coding category.
How many benchmarks do Granite 3.1 2b Instruct and Granite 4.0 H Small share?
12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Granite 4.0 H Small has 19.