Model comparison
Ministral 3B vs Phi-3.5-mini
Ministral 3B has enough public results to be ranked (#336); Phi-3.5-mini does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Mistral AI
MicrosoftSide by side
| Ministral 3B | Phi-3.5-mini | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 25.6 | 36.4 |
| Released | 2024-10-01 | 2024-08-16 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.04 | — |
| Output $ / M tokens | $0.04 | — |
| Results tracked | 6 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Ministral 3B: —, Phi-3.5-mini: 34.0 (#231)
| Benchmark | Ministral 3B | Phi-3.5-mini |
|---|---|---|
| BigCodeBench Instruct | — | 32.8% |
| BigCodeBench Complete | — | 38.5% |
Reasoning Not comparable
Ministral 3B: 17.7 (#278), Phi-3.5-mini: —
| Benchmark | Ministral 3B | Phi-3.5-mini |
|---|---|---|
| DTBench | 51.7% | — |
| LMCA | 5.5% | — |
| Epoch Capabilities Index | 118.08 | — |
| PIQA | — | 81% |
Math Not comparable
Ministral 3B: 24.5 (#257), Phi-3.5-mini: —
| Benchmark | Ministral 3B | Phi-3.5-mini |
|---|---|---|
| MATH Level 5 | 14.4% | — |
| GSM8K | — | 86.2% |
Knowledge Not comparable
Ministral 3B: 10.4 (#297), Phi-3.5-mini: —
| Benchmark | Ministral 3B | Phi-3.5-mini |
|---|---|---|
| GPQA Diamond | 25.3% | — |
| Vectara Hallucination Rate | 7.3% | — |
| BoolQ | — | 78% |
Frequently asked questions
Is Ministral 3B better than Phi-3.5-mini?
Ministral 3B has enough public results to be ranked (#336); Phi-3.5-mini does not yet, so treat this comparison as directional.
How many benchmarks do Ministral 3B and Phi-3.5-mini share?
0 benchmarks have published results for both models. Ministral 3B has 6 scored results on Noometry and Phi-3.5-mini has 5.