Model comparison
Granite 4.0 H Small vs Phi 3 Medium 4k Instruct
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 32.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
MicrosoftSummary
- They share 13 benchmarks with published results for both. Granite 4.0 H Small scores higher in 7 categories and Phi 3 Medium 4k Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Granite 4.0 H Small leads 68.9 to 57.8.
Side by side
| Granite 4.0 H Small | Phi 3 Medium 4k Instruct | |
|---|---|---|
| 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 | 17 |
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), Phi 3 Medium 4k Instruct: 32.3 (#263)
| Benchmark | Granite 4.0 H Small | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1247 | 1130 |
Reasoning Granite 4.0 H Small leads
Granite 4.0 H Small: 23.4 (#164), Phi 3 Medium 4k Instruct: 20.8 (#214)
| Benchmark | Granite 4.0 H Small | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1127 |
Math Phi 3 Medium 4k Instruct leads
Granite 4.0 H Small: 29.3 (#219), Phi 3 Medium 4k Instruct: 30.9 (#202)
| Benchmark | Granite 4.0 H Small | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1251 | 1173 |
| Omni-MATH | 29.6% | — |
Knowledge Granite 4.0 H Small leads
Granite 4.0 H Small: 31.5 (#210), Phi 3 Medium 4k Instruct: 29.6 (#226)
| Benchmark | Granite 4.0 H Small | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1244 | 1108 |
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |
Multilingual Granite 4.0 H Small leads
Granite 4.0 H Small: 38.7 (#223), Phi 3 Medium 4k Instruct: 30.8 (#258)
| Benchmark | Granite 4.0 H Small | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1216 | 1094 |
| LMArena Chinese | 1250 | 1108 |
| LMArena Russian | 1198 | 1145 |
| LMArena Spanish | 1258 | 1095 |
| LMArena French | — | 1109 |
| LMArena German | — | 1101 |
| LMArena Japanese | — | 1042 |
| LMArena Korean | — | 954 |
Instruction Following Granite 4.0 H Small leads
Granite 4.0 H Small: 68.9 (#178), Phi 3 Medium 4k Instruct: 57.8 (#263)
| Benchmark | Granite 4.0 H Small | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1221 | 1114 |
| IFEval | 89% | — |
Long Context Granite 4.0 H Small leads
Granite 4.0 H Small: 37.6 (#209), Phi 3 Medium 4k Instruct: 33.9 (#250)
| Benchmark | Granite 4.0 H Small | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1240 | 1120 |
Writing & Preference Granite 4.0 H Small leads
Granite 4.0 H Small: 44.0 (#222), Phi 3 Medium 4k Instruct: 34.3 (#267)
| Benchmark | Granite 4.0 H Small | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1241 | 1138 |
| LMArena Creative Writing | 1210 | 1106 |
| LMArena Multi-Turn | 1243 | 1088 |
| WildBench | 73.9% | — |
Frequently asked questions
Is Granite 4.0 H Small better than Phi 3 Medium 4k Instruct?
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 Phi 3 Medium 4k Instruct better for coding?
Granite 4.0 H Small scores higher on coding benchmarks: 35.8 versus 32.3 in the Noometry coding category.
How many benchmarks do Granite 4.0 H Small and Phi 3 Medium 4k Instruct share?
13 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.