Model comparison
Granite 4.1 8b vs Phi-4 Mini
Granite 4.1 8b is the stronger model overall, scoring 37.4 to 30.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
MicrosoftSummary
- The widest gap is in knowledge, where Granite 4.1 8b leads 36.1 to 25.3.
Side by side
| Granite 4.1 8b | Phi-4 Mini | |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 37.4 | 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 | 13 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.1 8b leads
Granite 4.1 8b: 30.1 (#297), Phi-4 Mini: 28.1 (#317)
| Benchmark | Granite 4.1 8b | Phi-4 Mini |
|---|---|---|
| LMArena WebDev | 1192 | — |
| SciCode | — | 10.8% |
| LMArena Coding | 1312 | — |
Reasoning Granite 4.1 8b leads
Granite 4.1 8b: 25.7 (#143), Phi-4 Mini: 22.4 (#195)
| Benchmark | Granite 4.1 8b | Phi-4 Mini |
|---|---|---|
| CritPt | — | 0% |
| LMArena Hard Prompts | 1293 | — |
Math Not comparable
Granite 4.1 8b: 36.4 (#166), Phi-4 Mini: —
| Benchmark | Granite 4.1 8b | Phi-4 Mini |
|---|---|---|
| LMArena Math | 1312 | — |
Knowledge Granite 4.1 8b leads
Granite 4.1 8b: 36.1 (#174), Phi-4 Mini: 25.3 (#262)
| Benchmark | Granite 4.1 8b | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | — | 23.5% |
| LMArena Expert | 1309 | — |
Multilingual Not comparable
Granite 4.1 8b: 41.7 (#204), Phi-4 Mini: —
| Benchmark | Granite 4.1 8b | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1261 | — |
| LMArena Chinese | 1337 | — |
| LMArena Russian | 1240 | — |
Instruction Following Not comparable
Granite 4.1 8b: 66.9 (#203), Phi-4 Mini: —
| Benchmark | Granite 4.1 8b | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1269 | — |
Long Context Not comparable
Granite 4.1 8b: 38.7 (#193), Phi-4 Mini: —
| Benchmark | Granite 4.1 8b | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1275 | — |
Writing & Preference Not comparable
Granite 4.1 8b: 48.1 (#204), Phi-4 Mini: —
| Benchmark | Granite 4.1 8b | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1290 | — |
| LMArena Creative Writing | 1251 | — |
| LMArena Multi-Turn | 1268 | — |
Frequently asked questions
Is Granite 4.1 8b better than Phi-4 Mini?
Granite 4.1 8b is the stronger model overall, scoring 37.4 to 30.9 on the Noometry Index.
Is Granite 4.1 8b or Phi-4 Mini better for coding?
Granite 4.1 8b scores higher on coding benchmarks: 30.1 versus 28.1 in the Noometry coding category.
How many benchmarks do Granite 4.1 8b and Phi-4 Mini share?
0 benchmarks have published results for both models. Granite 4.1 8b has 13 scored results on Noometry and Phi-4 Mini has 3.