Model comparison
Magistral Small vs Phi-3.5-mini
Magistral Small has enough public results to be ranked (#289); Phi-3.5-mini does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Mistral AI
MicrosoftSummary
- The widest gap is in coding, where Magistral Small leads 37.8 to 34.0.
Side by side
| Magistral Small | Phi-3.5-mini | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 29.9 | 36.4 |
| Released | 2025-06-10 | 2024-08-16 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 40K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 10 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Small leads
Magistral Small: 37.8 (#172), Phi-3.5-mini: 34.0 (#231)
| Benchmark | Magistral Small | Phi-3.5-mini |
|---|---|---|
| SciCode | 35.2% | — |
| BigCodeBench Instruct | — | 32.8% |
| BigCodeBench Complete | — | 38.5% |
Reasoning Not comparable
Magistral Small: 6.9 (#345), Phi-3.5-mini: —
| Benchmark | Magistral Small | Phi-3.5-mini |
|---|---|---|
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 6.3% | — |
| ARC-AGI-1 | 5% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 3% | — |
| DTBench | 61.3% | — |
| Epoch Capabilities Index | 133.19 | — |
| PIQA | — | 81% |
Math Not comparable
Magistral Small: 24.9 (#253), Phi-3.5-mini: —
| Benchmark | Magistral Small | Phi-3.5-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | — |
| GSM8K | — | 86.2% |
Knowledge Not comparable
Magistral Small: 30.9 (#215), Phi-3.5-mini: —
| Benchmark | Magistral Small | Phi-3.5-mini |
|---|---|---|
| GPQA Diamond | 56.1% | — |
| BoolQ | — | 78% |
Frequently asked questions
Is Magistral Small better than Phi-3.5-mini?
Magistral Small has enough public results to be ranked (#289); Phi-3.5-mini does not yet, so treat this comparison as directional.
Is Magistral Small or Phi-3.5-mini better for coding?
Magistral Small scores higher on coding benchmarks: 37.8 versus 34.0 in the Noometry coding category.
How many benchmarks do Magistral Small and Phi-3.5-mini share?
0 benchmarks have published results for both models. Magistral Small has 10 scored results on Noometry and Phi-3.5-mini has 5.