Model comparison
Magistral Small vs Phi 3 Mini 4k Instruct
Magistral Small is the stronger model overall, scoring 29.9 to 27.4 on the Noometry Index.
Last verified . 1 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 1 benchmark with published results for both. Magistral Small scores higher in 3 categories and Phi 3 Mini 4k Instruct in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in coding, where Magistral Small leads 37.8 to 26.1.
Side by side
| Magistral Small | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 29.9 | 27.4 |
| Released | 2025-06-10 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 40K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $1.50 | — |
| Results tracked | 10 | 35 |
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 Mini 4k Instruct: 26.1 (#319)
| Benchmark | Magistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| SciCode | 35.2% | — |
| LiveBench Coding | — | 15.5% |
| LMArena Coding | — | 1093 |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning Phi 3 Mini 4k Instruct leads
Magistral Small: 6.9 (#345), Phi 3 Mini 4k Instruct: 13.6 (#326)
| Benchmark | Magistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| Chess Puzzles | 3% | 0% |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 6.3% | — |
| ARC-AGI-1 | 5% | — |
| CritPt | 0.3% | — |
| LiveBench Reasoning | — | 26.8% |
| LMArena Hard Prompts | — | 1072 |
| DTBench | 61.3% | — |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 133.19 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Too close to call
Magistral Small: 24.9 (#253), Phi 3 Mini 4k Instruct: 24.5 (#258)
| Benchmark | Magistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 30% | — |
| LiveBench Math | — | 15.7% |
| LMArena Math | — | 1111 |
Knowledge Magistral Small leads
Magistral Small: 30.9 (#215), Phi 3 Mini 4k Instruct: 27.9 (#241)
| Benchmark | Magistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| GPQA Diamond | 56.1% | — |
| LMArena Expert | — | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Not comparable
Magistral Small: —, Phi 3 Mini 4k Instruct: 26.5 (#275)
| Benchmark | Magistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | — | 1021 |
| LMArena Chinese | — | 1021 |
| LMArena French | — | 1075 |
| LMArena German | — | 1044 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Russian | — | 1022 |
| LMArena Spanish | — | 1084 |
Instruction Following Not comparable
Magistral Small: —, Phi 3 Mini 4k Instruct: 48.0 (#298)
| Benchmark | Magistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | — | 39.1% |
| LMArena Instruction Following | — | 1053 |
Long Context Not comparable
Magistral Small: —, Phi 3 Mini 4k Instruct: 31.7 (#271)
| Benchmark | Magistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | — | 1044 |
Writing & Preference Not comparable
Magistral Small: —, Phi 3 Mini 4k Instruct: 27.7 (#295)
| Benchmark | Magistral Small | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | — | 1073 |
| LMArena Creative Writing | — | 1037 |
| LMArena Multi-Turn | — | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Magistral Small better than Phi 3 Mini 4k Instruct?
Magistral Small is the stronger model overall, scoring 29.9 to 27.4 on the Noometry Index.
Is Magistral Small or Phi 3 Mini 4k Instruct better for coding?
Magistral Small scores higher on coding benchmarks: 37.8 versus 26.1 in the Noometry coding category.
How many benchmarks do Magistral Small and Phi 3 Mini 4k Instruct share?
1 benchmark has published results for both models. Magistral Small has 10 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.