Model comparison
Granite 4.0 H Small vs StarCoder 2 7B
Granite 4.0 H Small has enough public results to be ranked (#213); StarCoder 2 7B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
NVIDIASide by side
| Granite 4.0 H Small | StarCoder 2 7B | |
|---|---|---|
| Provider | IBM | NVIDIA |
| Noometry Index | 35.9 | 36.5 |
| Released | — | 2024-02-20 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.0 H Small leads
Granite 4.0 H Small: 35.8 (#207), StarCoder 2 7B: 34.2
| Benchmark | Granite 4.0 H Small | StarCoder 2 7B |
|---|---|---|
| LMArena Coding | 1247 | — |
| BigCodeBench Complete | — | 27.7% |
| HumanEval+ | — | 29.9% |
Reasoning Not comparable
Granite 4.0 H Small: 23.4 (#164), StarCoder 2 7B: —
| Benchmark | Granite 4.0 H Small | StarCoder 2 7B |
|---|---|---|
| LMArena Hard Prompts | 1240 | — |
| Epoch Capabilities Index | — | 92.92 |
| WinoGrande | — | 57.1% |
Math Not comparable
Granite 4.0 H Small: 29.3 (#219), StarCoder 2 7B: —
| Benchmark | Granite 4.0 H Small | StarCoder 2 7B |
|---|---|---|
| Omni-MATH | 29.6% | — |
| LMArena Math | 1251 | — |
| GSM8K | — | 32.7% |
Knowledge Not comparable
Granite 4.0 H Small: 31.5 (#210), StarCoder 2 7B: —
| Benchmark | Granite 4.0 H Small | StarCoder 2 7B |
|---|---|---|
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |
| LMArena Expert | 1244 | — |
| ARC (AI2) Challenge | — | 38.7% |
| MMLU | — | 38.8% |
Multilingual Not comparable
Granite 4.0 H Small: 38.7 (#223), StarCoder 2 7B: —
| Benchmark | Granite 4.0 H Small | StarCoder 2 7B |
|---|---|---|
| LMArena Non-English | 1216 | — |
| LMArena Chinese | 1250 | — |
| LMArena Russian | 1198 | — |
| LMArena Spanish | 1258 | — |
Instruction Following Not comparable
Granite 4.0 H Small: 68.9 (#178), StarCoder 2 7B: —
| Benchmark | Granite 4.0 H Small | StarCoder 2 7B |
|---|---|---|
| IFEval | 89% | — |
| LMArena Instruction Following | 1221 | — |
Long Context Not comparable
Granite 4.0 H Small: 37.6 (#209), StarCoder 2 7B: —
| Benchmark | Granite 4.0 H Small | StarCoder 2 7B |
|---|---|---|
| LMArena Longer Query | 1240 | — |
Writing & Preference Not comparable
Granite 4.0 H Small: 44.0 (#222), StarCoder 2 7B: —
| Benchmark | Granite 4.0 H Small | StarCoder 2 7B |
|---|---|---|
| LMArena Text | 1241 | — |
| LMArena Creative Writing | 1210 | — |
| WildBench | 73.9% | — |
| LMArena Multi-Turn | 1243 | — |
Frequently asked questions
Is Granite 4.0 H Small better than StarCoder 2 7B?
Granite 4.0 H Small has enough public results to be ranked (#213); StarCoder 2 7B does not yet, so treat this comparison as directional.
Is Granite 4.0 H Small or StarCoder 2 7B better for coding?
Granite 4.0 H Small scores higher on coding benchmarks: 35.8 versus 34.2 in the Noometry coding category.
How many benchmarks do Granite 4.0 H Small and StarCoder 2 7B share?
0 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and StarCoder 2 7B has 7.