Model comparison
Granite 3.0 2b Instruct vs Granite 4.0 H Small
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 30.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Granite 3.0 2b Instruct scores higher in 1 category and Granite 4.0 H Small in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Granite 4.0 H Small leads 68.7 to 53.9.
Side by side
| Granite 3.0 2b Instruct | Granite 4.0 H Small | |
|---|---|---|
| Provider | IBM | IBM |
| Noometry Index | 30.8 | 36.5 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.0 H Small leads
Granite 3.0 2b Instruct: 28.3 (#316), Granite 4.0 H Small: 36.4 (#209)
| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | 1090 | 1249 |
| BigCodeBench Instruct | 20.5% | — |
Reasoning Granite 4.0 H Small leads
Granite 3.0 2b Instruct: 20.5 (#235), Granite 4.0 H Small: 24.4 (#163)
| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1240 |
Math Too close to call
Granite 3.0 2b Instruct: 32.2 (#217), Granite 4.0 H Small: 31.4 (#223)
| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Math | 1117 | 1247 |
| Omni-MATH | — | 29.6% |
Knowledge Granite 4.0 H Small leads
Granite 3.0 2b Instruct: 29.0 (#241), Granite 4.0 H Small: 32.0 (#215)
| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Expert | 1064 | 1251 |
| MMLU-Pro | — | 56.9% |
| Vectara Hallucination Rate | — | 5.2% |
| GPQA (HELM) | — | 38.3% |
Multilingual Granite 4.0 H Small leads
Granite 3.0 2b Instruct: 27.0 (#278), Granite 4.0 H Small: 38.6 (#228)
| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | 1033 | 1216 |
| LMArena Chinese | 1070 | 1249 |
| LMArena Russian | 1045 | 1201 |
| LMArena Spanish | — | 1258 |
Instruction Following Granite 4.0 H Small leads
Granite 3.0 2b Instruct: 53.9 (#284), Granite 4.0 H Small: 68.7 (#183)
| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Instruction Following | 1056 | 1222 |
| IFEval | — | 89% |
Long Context Granite 4.0 H Small leads
Granite 3.0 2b Instruct: 32.5 (#268), Granite 4.0 H Small: 37.7 (#213)
| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | 1070 | 1242 |
Writing & Preference Granite 4.0 H Small leads
Granite 3.0 2b Instruct: 29.6 (#292), Granite 4.0 H Small: 43.8 (#227)
| Benchmark | Granite 3.0 2b Instruct | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | 1080 | 1241 |
| LMArena Creative Writing | 1046 | 1211 |
| LMArena Multi-Turn | 1053 | 1242 |
| WildBench | — | 73.9% |
Frequently asked questions
Is Granite 3.0 2b Instruct better than Granite 4.0 H Small?
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 30.8 on the Noometry Index.
Is Granite 3.0 2b Instruct or Granite 4.0 H Small better for coding?
Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 28.3 in the Noometry coding category.
How many benchmarks do Granite 3.0 2b Instruct and Granite 4.0 H Small share?
12 benchmarks have published results for both models. Granite 3.0 2b Instruct has 13 scored results on Noometry and Granite 4.0 H Small has 19.