Model comparison
Granite 4.0 H Small vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.4 to 35.9 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 2 categories and QwQ-32B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in long context, where QwQ-32B leads 49.0 to 37.6.
Side by side
| Granite 4.0 H Small | QwQ-32B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 35.9 | 39.4 |
| Released | — | 2024-11-28 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Granite 4.0 H Small: 35.8 (#207), QwQ-32B: 34.9 (#220)
| Benchmark | Granite 4.0 H Small | QwQ-32B |
|---|---|---|
| LMArena Coding | 1247 | 1333 |
| Aider Polyglot | — | 20.9% |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
Reasoning Too close to call
Granite 4.0 H Small: 23.4 (#164), QwQ-32B: 22.9 (#171)
| Benchmark | Granite 4.0 H Small | QwQ-32B |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1326 |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | — | 83.5% |
| LiveBench Data Analysis | — | 65% |
| Epoch Capabilities Index | — | 137.6 |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |
Math QwQ-32B leads
Granite 4.0 H Small: 29.3 (#219), QwQ-32B: 36.2 (#123)
| Benchmark | Granite 4.0 H Small | QwQ-32B |
|---|---|---|
| LMArena Math | 1251 | 1359 |
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| Omni-MATH | 29.6% | — |
| LiveBench Math | — | 77.8% |
Knowledge QwQ-32B leads
Granite 4.0 H Small: 31.5 (#210), QwQ-32B: 37.2 (#150)
| Benchmark | Granite 4.0 H Small | QwQ-32B |
|---|---|---|
| LMArena Expert | 1244 | 1323 |
| GPQA Diamond | — | 65.3% |
| MMLU-Pro | 56.9% | — |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |
Multilingual QwQ-32B leads
Granite 4.0 H Small: 38.7 (#223), QwQ-32B: 45.0 (#171)
| Benchmark | Granite 4.0 H Small | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1216 | 1306 |
| LMArena Chinese | 1250 | 1378 |
| LMArena Russian | 1198 | 1297 |
| LMArena Spanish | 1258 | 1353 |
| LMArena French | — | 1337 |
| LMArena German | — | 1313 |
| LMArena Japanese | — | 1263 |
| LMArena Korean | — | 1278 |
Instruction Following QwQ-32B leads
Granite 4.0 H Small: 68.9 (#178), QwQ-32B: 72.8 (#131)
| Benchmark | Granite 4.0 H Small | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1221 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
| IFEval | 89% | — |
Long Context QwQ-32B leads
Granite 4.0 H Small: 37.6 (#209), QwQ-32B: 49.0 (#11)
| Benchmark | Granite 4.0 H Small | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1240 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference QwQ-32B leads
Granite 4.0 H Small: 44.0 (#222), QwQ-32B: 50.9 (#175)
| Benchmark | Granite 4.0 H Small | QwQ-32B |
|---|---|---|
| LMArena Text | 1241 | 1329 |
| LMArena Creative Writing | 1210 | 1288 |
| LMArena Multi-Turn | 1243 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| WildBench | 73.9% | — |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is Granite 4.0 H Small better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.4 to 35.9 on the Noometry Index.
Is Granite 4.0 H Small or QwQ-32B better for coding?
They score almost the same on coding (35.8 vs 34.9); test both on your own repository before choosing.
How many benchmarks do Granite 4.0 H Small and QwQ-32B share?
13 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and QwQ-32B has 36.