Model comparison
Ministral 3B vs Phi-4 Mini
Phi-4 Mini is the stronger model overall, scoring 30.4 to 25.6 on the Noometry Index. Ministral 3B costs 3.3× less per token, which makes it the better buy when Phi-4 Mini's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 1 benchmark with published results for both. Ministral 3B scores higher in 0 categories and Phi-4 Mini in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi-4 Mini leads 24.8 to 10.4.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 7.3% for Ministral 3B and 23.5% for Phi-4 Mini.
- Ministral 3B is cheaper at $0.04 / $0.04 per million input/output tokens, against $0.075 / $0.30 for Phi-4 Mini.
Side by side
| Ministral 3B | Phi-4 Mini | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 25.6 | 30.4 |
| Released | 2024-10-01 | 2024-12-11 |
| Weights | Open | Open |
| Context window | 128K | 128K |
| Max output | 128K | 4K |
| Input $ / M tokens | $0.04 | $0.075 |
| Output $ / M tokens | $0.04 | $0.30 |
| Results tracked | 6 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Ministral 3B: —, Phi-4 Mini: 27.6 (#312)
| Benchmark | Ministral 3B | Phi-4 Mini |
|---|---|---|
| SciCode | — | 10.8% |
Reasoning Phi-4 Mini leads
Ministral 3B: 17.7 (#278), Phi-4 Mini: 21.7 (#190)
| Benchmark | Ministral 3B | Phi-4 Mini |
|---|---|---|
| CritPt | — | 0% |
| DTBench | 51.7% | — |
| LMCA | 5.5% | — |
| Epoch Capabilities Index | 118.08 | — |
Math Not comparable
Ministral 3B: 24.5 (#257), Phi-4 Mini: —
| Benchmark | Ministral 3B | Phi-4 Mini |
|---|---|---|
| MATH Level 5 | 14.4% | — |
Knowledge Phi-4 Mini leads
Ministral 3B: 10.4 (#297), Phi-4 Mini: 24.8 (#261)
| Benchmark | Ministral 3B | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | 7.3% | 23.5% |
| GPQA Diamond | 25.3% | — |
Frequently asked questions
Is Ministral 3B better than Phi-4 Mini?
Phi-4 Mini is the stronger model overall, scoring 30.4 to 25.6 on the Noometry Index. Ministral 3B costs 3.3× less per token, which makes it the better buy when Phi-4 Mini's lead doesn't matter for your workload.
Which is cheaper, Ministral 3B or Phi-4 Mini?
Ministral 3B is cheaper. It lists at $0.04 per million input tokens and $0.04 per million output tokens; Phi-4 Mini lists at $0.075 and $0.30.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Ministral 3B and Phi-4 Mini share?
1 benchmark has published results for both models. Ministral 3B has 6 scored results on Noometry and Phi-4 Mini has 3.