Model comparison
Granite 4.0 H Small vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 38.8 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 1 category and Qwen3 32B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 32B leads 53.1 to 44.0.
Side by side
| Granite 4.0 H Small | Qwen3 32B | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 35.9 | 38.8 |
| Released | — | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 19 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Granite 4.0 H Small: 35.8 (#207), Qwen3 32B: 37.3 (#184)
| Benchmark | Granite 4.0 H Small | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1247 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
Agentic & Tool Use Not comparable
Granite 4.0 H Small: —, Qwen3 32B: 32.3 (#58)
| Benchmark | Granite 4.0 H Small | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Granite 4.0 H Small leads
Granite 4.0 H Small: 23.4 (#164), Qwen3 32B: 19.6 (#233)
| Benchmark | Granite 4.0 H Small | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1335 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |
Math Qwen3 32B leads
Granite 4.0 H Small: 29.3 (#219), Qwen3 32B: 37.9 (#89)
| Benchmark | Granite 4.0 H Small | Qwen3 32B |
|---|---|---|
| LMArena Math | 1251 | 1399 |
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| Omni-MATH | 29.6% | — |
Knowledge Qwen3 32B leads
Granite 4.0 H Small: 31.5 (#210), Qwen3 32B: 40.0 (#112)
| Benchmark | Granite 4.0 H Small | Qwen3 32B |
|---|---|---|
| Vectara Hallucination Rate | 5.2% | 5.9% |
| LMArena Expert | 1244 | 1362 |
| GPQA Diamond | — | 65.7% |
| MMLU-Pro | 56.9% | — |
| GPQA (HELM) | 38.3% | — |
Multilingual Qwen3 32B leads
Granite 4.0 H Small: 38.7 (#223), Qwen3 32B: 45.8 (#162)
| Benchmark | Granite 4.0 H Small | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1216 | 1317 |
| LMArena Chinese | 1250 | 1357 |
| LMArena Russian | 1198 | 1311 |
| LMArena German | — | 1341 |
| LMArena Spanish | 1258 | — |
Instruction Following Too close to call
Granite 4.0 H Small: 68.9 (#178), Qwen3 32B: 69.1 (#174)
| Benchmark | Granite 4.0 H Small | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1221 | 1305 |
| IFEval | 89% | — |
Long Context Qwen3 32B leads
Granite 4.0 H Small: 37.6 (#209), Qwen3 32B: 43.7 (#83)
| Benchmark | Granite 4.0 H Small | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1240 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Qwen3 32B leads
Granite 4.0 H Small: 44.0 (#222), Qwen3 32B: 53.1 (#158)
| Benchmark | Granite 4.0 H Small | Qwen3 32B |
|---|---|---|
| LMArena Text | 1241 | 1340 |
| LMArena Creative Writing | 1210 | 1297 |
| LMArena Multi-Turn | 1243 | 1331 |
| WildBench | 73.9% | — |
Frequently asked questions
Is Granite 4.0 H Small better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 38.8 to 35.9 on the Noometry Index.
Is Granite 4.0 H Small or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.3 versus 35.8 in the Noometry coding category.
How many benchmarks do Granite 4.0 H Small and Qwen3 32B share?
13 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Qwen3 32B has 26.