Model comparison
Granite 4.0 H Small vs Wizardlm 70b
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 32.4 on the Noometry Index.
Last verified . 11 shared benchmarks.
MicrosoftSummary
- They share 11 benchmarks with published results for both. Granite 4.0 H Small scores higher in 6 categories and Wizardlm 70b in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Granite 4.0 H Small leads 68.9 to 56.5.
Side by side
| Granite 4.0 H Small | Wizardlm 70b | |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 35.9 | 32.4 |
| Released | — | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 12 |
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), Wizardlm 70b: 30.9 (#280)
| Benchmark | Granite 4.0 H Small | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1247 | 1081 |
Reasoning Granite 4.0 H Small leads
Granite 4.0 H Small: 23.4 (#164), Wizardlm 70b: 19.8 (#231)
| Benchmark | Granite 4.0 H Small | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1079 |
Math Too close to call
Granite 4.0 H Small: 29.3 (#219), Wizardlm 70b: 29.7 (#216)
| Benchmark | Granite 4.0 H Small | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1251 | 1116 |
| Omni-MATH | 29.6% | — |
Knowledge Not comparable
Granite 4.0 H Small: 31.5 (#210), Wizardlm 70b: —
| Benchmark | Granite 4.0 H Small | Wizardlm 70b |
|---|---|---|
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |
| LMArena Expert | 1244 | — |
Multilingual Granite 4.0 H Small leads
Granite 4.0 H Small: 38.7 (#223), Wizardlm 70b: 29.8 (#260)
| Benchmark | Granite 4.0 H Small | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1216 | 1078 |
| LMArena Chinese | 1250 | 1052 |
| LMArena Russian | 1198 | 1155 |
| LMArena German | — | 1083 |
| LMArena Spanish | 1258 | — |
Instruction Following Granite 4.0 H Small leads
Granite 4.0 H Small: 68.9 (#178), Wizardlm 70b: 56.5 (#268)
| Benchmark | Granite 4.0 H Small | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1221 | 1093 |
| IFEval | 89% | — |
Long Context Granite 4.0 H Small leads
Granite 4.0 H Small: 37.6 (#209), Wizardlm 70b: 33.3 (#258)
| Benchmark | Granite 4.0 H Small | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1240 | 1097 |
Writing & Preference Granite 4.0 H Small leads
Granite 4.0 H Small: 44.0 (#222), Wizardlm 70b: 34.9 (#264)
| Benchmark | Granite 4.0 H Small | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1241 | 1120 |
| LMArena Creative Writing | 1210 | 1149 |
| LMArena Multi-Turn | 1243 | 1108 |
| WildBench | 73.9% | — |
Frequently asked questions
Is Granite 4.0 H Small better than Wizardlm 70b?
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 32.4 on the Noometry Index.
Is Granite 4.0 H Small or Wizardlm 70b better for coding?
Granite 4.0 H Small scores higher on coding benchmarks: 35.8 versus 30.9 in the Noometry coding category.
How many benchmarks do Granite 4.0 H Small and Wizardlm 70b share?
11 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Wizardlm 70b has 12.