Model comparison
Granite 4.0 H Small vs Qwen2.5 Plus 1127
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.1 to 35.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Granite 4.0 H Small scores higher in 1 category and Qwen2.5 Plus 1127 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 Plus 1127 leads 49.5 to 44.0.
- Granite 4.0 H Small has downloadable open weights; the other is API-only.
Side by side
| Granite 4.0 H Small | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 35.9 | 38.1 |
| Released | — | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 Plus 1127 leads
Granite 4.0 H Small: 35.8 (#207), Qwen2.5 Plus 1127: 37.9 (#171)
| Benchmark | Granite 4.0 H Small | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Coding | 1247 | 1314 |
Reasoning Qwen2.5 Plus 1127 leads
Granite 4.0 H Small: 23.4 (#164), Qwen2.5 Plus 1127: 24.8 (#139)
| Benchmark | Granite 4.0 H Small | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1299 |
Math Qwen2.5 Plus 1127 leads
Granite 4.0 H Small: 29.3 (#219), Qwen2.5 Plus 1127: 33.5 (#175)
| Benchmark | Granite 4.0 H Small | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | 1251 | 1298 |
| Omni-MATH | 29.6% | — |
Knowledge Qwen2.5 Plus 1127 leads
Granite 4.0 H Small: 31.5 (#210), Qwen2.5 Plus 1127: 34.9 (#179)
| Benchmark | Granite 4.0 H Small | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | 1244 | 1289 |
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |
Multilingual Qwen2.5 Plus 1127 leads
Granite 4.0 H Small: 38.7 (#223), Qwen2.5 Plus 1127: 42.1 (#196)
| Benchmark | Granite 4.0 H Small | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | 1216 | 1265 |
| LMArena Chinese | 1250 | 1314 |
| LMArena Russian | 1198 | 1271 |
| LMArena German | — | 1231 |
| LMArena Japanese | — | 1207 |
| LMArena Spanish | 1258 | — |
Instruction Following Granite 4.0 H Small leads
Granite 4.0 H Small: 68.9 (#178), Qwen2.5 Plus 1127: 67.4 (#194)
| Benchmark | Granite 4.0 H Small | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | 1221 | 1275 |
| IFEval | 89% | — |
Long Context Qwen2.5 Plus 1127 leads
Granite 4.0 H Small: 37.6 (#209), Qwen2.5 Plus 1127: 39.2 (#180)
| Benchmark | Granite 4.0 H Small | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | 1240 | 1292 |
Writing & Preference Qwen2.5 Plus 1127 leads
Granite 4.0 H Small: 44.0 (#222), Qwen2.5 Plus 1127: 49.5 (#186)
| Benchmark | Granite 4.0 H Small | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | 1241 | 1299 |
| LMArena Creative Writing | 1210 | 1262 |
| LMArena Multi-Turn | 1243 | 1299 |
| WildBench | 73.9% | — |
Frequently asked questions
Is Granite 4.0 H Small better than Qwen2.5 Plus 1127?
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.1 to 35.9 on the Noometry Index.
Is Granite 4.0 H Small or Qwen2.5 Plus 1127 better for coding?
Qwen2.5 Plus 1127 scores higher on coding benchmarks: 37.9 versus 35.8 in the Noometry coding category.
How many benchmarks do Granite 4.0 H Small and Qwen2.5 Plus 1127 share?
12 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Qwen2.5 Plus 1127 has 14.