Model comparison
Granite 4.0 Micro vs Phi-3.5-mini
Granite 4.0 Micro has enough public results to be ranked (#312); Phi-3.5-mini does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Side by side
| Granite 4.0 Micro | Phi-3.5-mini | |
|---|---|---|
| Provider | IBM | Microsoft |
| Noometry Index | 28.8 | 36.4 |
| Released | 2025-10-02 | 2024-08-16 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.017 | — |
| Output $ / M tokens | $0.11 | — |
| Results tracked | 8 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Granite 4.0 Micro: —, Phi-3.5-mini: 34.0 (#231)
| Benchmark | Granite 4.0 Micro | Phi-3.5-mini |
|---|---|---|
| BigCodeBench Instruct | — | 32.8% |
| BigCodeBench Complete | — | 38.5% |
Reasoning Not comparable
Granite 4.0 Micro: 18.5 (#261), Phi-3.5-mini: —
| Benchmark | Granite 4.0 Micro | Phi-3.5-mini |
|---|---|---|
| Chess Puzzles | 0% | — |
| PIQA | — | 81% |
Math Not comparable
Granite 4.0 Micro: 11.2 (#301), Phi-3.5-mini: —
| Benchmark | Granite 4.0 Micro | Phi-3.5-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.8% | — |
| Omni-MATH | 20.9% | — |
| GSM8K | — | 86.2% |
Knowledge Not comparable
Granite 4.0 Micro: 9.9 (#299), Phi-3.5-mini: —
| Benchmark | Granite 4.0 Micro | Phi-3.5-mini |
|---|---|---|
| GPQA Diamond | 28.3% | — |
| MMLU-Pro | 39.5% | — |
| GPQA (HELM) | 30.7% | — |
| BoolQ | — | 78% |
Instruction Following Not comparable
Granite 4.0 Micro: 70.0 (#164), Phi-3.5-mini: —
| Benchmark | Granite 4.0 Micro | Phi-3.5-mini |
|---|---|---|
| IFEval | 84.9% | — |
Writing & Preference Not comparable
Granite 4.0 Micro: 46.7 (#212), Phi-3.5-mini: —
| Benchmark | Granite 4.0 Micro | Phi-3.5-mini |
|---|---|---|
| WildBench | 67% | — |
Frequently asked questions
Is Granite 4.0 Micro better than Phi-3.5-mini?
Granite 4.0 Micro has enough public results to be ranked (#312); Phi-3.5-mini does not yet, so treat this comparison as directional.
How many benchmarks do Granite 4.0 Micro and Phi-3.5-mini share?
0 benchmarks have published results for both models. Granite 4.0 Micro has 8 scored results on Noometry and Phi-3.5-mini has 5.