Model comparison
Ministral 3B vs Phi-2
Ministral 3B has enough public results to be ranked (#338); Phi-2 does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 1 benchmark with published results for both.
Side by side
| Ministral 3B | Phi-2 | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 26.2 | — |
| Released | 2024-10-01 | 2023-12-12 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.10 | — |
| Results tracked | 6 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Ministral 3B: —, Phi-2: —
| Benchmark | Ministral 3B | Phi-2 |
|---|---|---|
| HumanEval+ | — | 45.1% |
| MBPP+ | — | 54.2% |
Reasoning Not comparable
Ministral 3B: 18.4 (#282), Phi-2: —
| Benchmark | Ministral 3B | Phi-2 |
|---|---|---|
| Epoch Capabilities Index | 118.1 | 107.94 |
| DTBench | 51.7% | — |
| LMCA | 5.5% | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| HellaSwag | — | 53.6% |
| WinoGrande | — | 54.7% |
Math Not comparable
Ministral 3B: 26.6 (#258), Phi-2: —
| Benchmark | Ministral 3B | Phi-2 |
|---|---|---|
| MATH Level 5 | 14.4% | — |
Knowledge Not comparable
Ministral 3B: 10.4 (#302), Phi-2: —
| Benchmark | Ministral 3B | Phi-2 |
|---|---|---|
| GPQA Diamond | 25.3% | — |
| Vectara Hallucination Rate | 7.3% | — |
| ARC (AI2) Challenge | — | 75.9% |
| MMLU | — | 58.4% |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |
Frequently asked questions
Is Ministral 3B better than Phi-2?
Ministral 3B has enough public results to be ranked (#338); Phi-2 does not yet, so treat this comparison as directional.
How many benchmarks do Ministral 3B and Phi-2 share?
1 benchmark has published results for both models. Ministral 3B has 6 scored results on Noometry and Phi-2 has 11.