Model comparison
Granite 4.2 30b vs Phi-4 Mini
Granite 4.2 30b is the stronger model overall, scoring 41.8 to 30.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in knowledge, where Granite 4.2 30b leads 39.1 to 25.3.
Side by side
| Granite 4.2 30b | Phi-4 Mini | |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 41.8 | 30.9 |
| Released | — | 2024-12-11 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.075 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 11 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 30b leads
Granite 4.2 30b: 41.0 (#126), Phi-4 Mini: 28.1 (#317)
| Benchmark | Granite 4.2 30b | Phi-4 Mini |
|---|---|---|
| SciCode | — | 10.8% |
| LMArena Coding | 1396 | — |
Reasoning Granite 4.2 30b leads
Granite 4.2 30b: 27.8 (#112), Phi-4 Mini: 22.4 (#195)
| Benchmark | Granite 4.2 30b | Phi-4 Mini |
|---|---|---|
| CritPt | — | 0% |
| LMArena Hard Prompts | 1374 | — |
Knowledge Granite 4.2 30b leads
Granite 4.2 30b: 39.1 (#138), Phi-4 Mini: 25.3 (#262)
| Benchmark | Granite 4.2 30b | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | — | 23.5% |
| LMArena Expert | 1406 | — |
Multilingual Not comparable
Granite 4.2 30b: 47.3 (#151), Phi-4 Mini: —
| Benchmark | Granite 4.2 30b | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1340 | — |
| LMArena Chinese | 1414 | — |
| LMArena Russian | 1343 | — |
Instruction Following Not comparable
Granite 4.2 30b: 71.2 (#155), Phi-4 Mini: —
| Benchmark | Granite 4.2 30b | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1347 | — |
Long Context Not comparable
Granite 4.2 30b: 41.4 (#140), Phi-4 Mini: —
| Benchmark | Granite 4.2 30b | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1359 | — |
Writing & Preference Not comparable
Granite 4.2 30b: 53.8 (#156), Phi-4 Mini: —
| Benchmark | Granite 4.2 30b | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1361 | — |
| LMArena Creative Writing | 1288 | — |
| LMArena Multi-Turn | 1339 | — |
Frequently asked questions
Is Granite 4.2 30b better than Phi-4 Mini?
Granite 4.2 30b is the stronger model overall, scoring 41.8 to 30.9 on the Noometry Index.
Is Granite 4.2 30b or Phi-4 Mini better for coding?
Granite 4.2 30b scores higher on coding benchmarks: 41.0 versus 28.1 in the Noometry coding category.
How many benchmarks do Granite 4.2 30b and Phi-4 Mini share?
0 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and Phi-4 Mini has 3.