Model comparison
Granite 4.0 H Small vs Qwen2-72B
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 29.5 on the Noometry Index.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Granite 4.0 H Small scores higher in 8 categories and Qwen2-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.0 H Small leads 31.5 to 21.2.
Side by side
| Granite 4.0 H Small | Qwen2-72B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 35.9 | 29.5 |
| Released | — | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 26 |
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), Qwen2-72B: 28.7 (#303)
| Benchmark | Granite 4.0 H Small | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1247 | 1196 |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Not comparable
Granite 4.0 H Small: —, Qwen2-72B: 16.9 (#138)
| Benchmark | Granite 4.0 H Small | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Granite 4.0 H Small leads
Granite 4.0 H Small: 23.4 (#164), Qwen2-72B: 22.2 (#184)
| Benchmark | Granite 4.0 H Small | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1191 |
| Epoch Capabilities Index | — | 125.27 |
Math Granite 4.0 H Small leads
Granite 4.0 H Small: 29.3 (#219), Qwen2-72B: 27.9 (#232)
| Benchmark | Granite 4.0 H Small | Qwen2-72B |
|---|---|---|
| LMArena Math | 1251 | 1235 |
| Omni-MATH | 29.6% | — |
| MATH Level 5 | — | 39.1% |
Knowledge Granite 4.0 H Small leads
Granite 4.0 H Small: 31.5 (#210), Qwen2-72B: 21.2 (#270)
| Benchmark | Granite 4.0 H Small | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1244 | 1171 |
| GPQA Diamond | — | 40.8% |
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |
| MMLU | — | 82.4% |
Multilingual Granite 4.0 H Small leads
Granite 4.0 H Small: 38.7 (#223), Qwen2-72B: 36.0 (#239)
| Benchmark | Granite 4.0 H Small | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1216 | 1176 |
| LMArena Chinese | 1250 | 1240 |
| LMArena Russian | 1198 | 1169 |
| LMArena Spanish | 1258 | 1168 |
| LMArena French | — | 1169 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
Instruction Following Granite 4.0 H Small leads
Granite 4.0 H Small: 68.9 (#178), Qwen2-72B: 62.0 (#236)
| Benchmark | Granite 4.0 H Small | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1221 | 1181 |
| IFEval | 89% | — |
Long Context Granite 4.0 H Small leads
Granite 4.0 H Small: 37.6 (#209), Qwen2-72B: 36.1 (#230)
| Benchmark | Granite 4.0 H Small | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1240 | 1193 |
Writing & Preference Granite 4.0 H Small leads
Granite 4.0 H Small: 44.0 (#222), Qwen2-72B: 41.0 (#236)
| Benchmark | Granite 4.0 H Small | Qwen2-72B |
|---|---|---|
| LMArena Text | 1241 | 1203 |
| LMArena Creative Writing | 1210 | 1181 |
| LMArena Multi-Turn | 1243 | 1195 |
| WildBench | 73.9% | — |
Frequently asked questions
Is Granite 4.0 H Small better than Qwen2-72B?
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 29.5 on the Noometry Index.
Is Granite 4.0 H Small or Qwen2-72B better for coding?
Granite 4.0 H Small scores higher on coding benchmarks: 35.8 versus 28.7 in the Noometry coding category.
How many benchmarks do Granite 4.0 H Small and Qwen2-72B share?
13 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Qwen2-72B has 26.