Model comparison
Granite 4.0 H Small vs phi-3-medium 14B
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 29.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in knowledge, where Granite 4.0 H Small leads 31.5 to 9.1.
Side by side
| Granite 4.0 H Small | phi-3-medium 14B | |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 35.9 | 29.1 |
| Released | — | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 13 |
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), phi-3-medium 14B: 36.3 (#198)
| Benchmark | Granite 4.0 H Small | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1247 | — |
| BigCodeBench Complete | — | 48.7% |
Reasoning Not comparable
Granite 4.0 H Small: 23.4 (#164), phi-3-medium 14B: —
| Benchmark | Granite 4.0 H Small | phi-3-medium 14B |
|---|---|---|
| LMArena Hard Prompts | 1240 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.18 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |
Math Granite 4.0 H Small leads
Granite 4.0 H Small: 29.3 (#219), phi-3-medium 14B: 25.2 (#249)
| Benchmark | Granite 4.0 H Small | phi-3-medium 14B |
|---|---|---|
| Omni-MATH | 29.6% | — |
| LMArena Math | 1251 | — |
| MATH Level 5 | — | 17.6% |
Knowledge Granite 4.0 H Small leads
Granite 4.0 H Small: 31.5 (#210), phi-3-medium 14B: 9.1 (#301)
| Benchmark | Granite 4.0 H Small | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| MMLU-Pro | 56.9% | — |
| Vectara Hallucination Rate | 5.2% | — |
| GPQA (HELM) | 38.3% | — |
| LMArena Expert | 1244 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |
Multilingual Not comparable
Granite 4.0 H Small: 38.7 (#223), phi-3-medium 14B: —
| Benchmark | Granite 4.0 H Small | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1216 | — |
| LMArena Chinese | 1250 | — |
| LMArena Russian | 1198 | — |
| LMArena Spanish | 1258 | — |
Instruction Following Not comparable
Granite 4.0 H Small: 68.9 (#178), phi-3-medium 14B: —
| Benchmark | Granite 4.0 H Small | phi-3-medium 14B |
|---|---|---|
| IFEval | 89% | — |
| LMArena Instruction Following | 1221 | — |
Long Context Not comparable
Granite 4.0 H Small: 37.6 (#209), phi-3-medium 14B: —
| Benchmark | Granite 4.0 H Small | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1240 | — |
Writing & Preference Not comparable
Granite 4.0 H Small: 44.0 (#222), phi-3-medium 14B: —
| Benchmark | Granite 4.0 H Small | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1241 | — |
| LMArena Creative Writing | 1210 | — |
| WildBench | 73.9% | — |
| LMArena Multi-Turn | 1243 | — |
Frequently asked questions
Is Granite 4.0 H Small better than phi-3-medium 14B?
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 29.1 on the Noometry Index.
Is Granite 4.0 H Small or phi-3-medium 14B better for coding?
They score almost the same on coding (35.8 vs 36.3); test both on your own repository before choosing.
How many benchmarks do Granite 4.0 H Small and phi-3-medium 14B share?
0 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and phi-3-medium 14B has 13.