Model comparison
Magistral Medium vs Phi 3 Medium 4k Instruct
Magistral Medium is the stronger model overall, scoring 35.2 to 33.0 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AI
MicrosoftSummary
- They share 17 benchmarks with published results for both. Magistral Medium scores higher in 7 categories and Phi 3 Medium 4k Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Phi 3 Medium 4k Instruct leads 21.7 to 8.6.
Side by side
| Magistral Medium | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | Mistral AI | Microsoft |
| Noometry Index | 35.2 | 33.0 |
| Released | 2025-03-17 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 16K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $5 | — |
| Results tracked | 22 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Magistral Medium: 39.1 (#161), Phi 3 Medium 4k Instruct: 32.9 (#268)
| Benchmark | Magistral Medium | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1319 | 1130 |
| SciCode | 39.2% | — |
Reasoning Phi 3 Medium 4k Instruct leads
Magistral Medium: 8.6 (#348), Phi 3 Medium 4k Instruct: 21.7 (#214)
| Benchmark | Magistral Medium | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1127 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
Math Magistral Medium leads
Magistral Medium: 35.1 (#189), Phi 3 Medium 4k Instruct: 33.4 (#202)
| Benchmark | Magistral Medium | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1250 | 1173 |
Knowledge Magistral Medium leads
Magistral Medium: 33.5 (#202), Phi 3 Medium 4k Instruct: 30.2 (#229)
| Benchmark | Magistral Medium | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1223 | 1108 |
Multilingual Magistral Medium leads
Magistral Medium: 39.6 (#224), Phi 3 Medium 4k Instruct: 30.6 (#263)
| Benchmark | Magistral Medium | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1232 | 1094 |
| LMArena Chinese | 1227 | 1108 |
| LMArena French | 1267 | 1110 |
| LMArena German | 1248 | 1101 |
| LMArena Japanese | 1175 | 1042 |
| LMArena Korean | 1125 | 954 |
| LMArena Russian | 1224 | 1145 |
| LMArena Spanish | 1271 | 1095 |
Instruction Following Magistral Medium leads
Magistral Medium: 66.0 (#211), Phi 3 Medium 4k Instruct: 57.6 (#268)
| Benchmark | Magistral Medium | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1254 | 1113 |
Long Context Magistral Medium leads
Magistral Medium: 39.3 (#183), Phi 3 Medium 4k Instruct: 34.0 (#255)
| Benchmark | Magistral Medium | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1295 | 1120 |
Writing & Preference Magistral Medium leads
Magistral Medium: 46.3 (#219), Phi 3 Medium 4k Instruct: 34.1 (#272)
| Benchmark | Magistral Medium | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1255 | 1138 |
| LMArena Creative Writing | 1245 | 1107 |
| LMArena Multi-Turn | 1275 | 1088 |
Frequently asked questions
Is Magistral Medium better than Phi 3 Medium 4k Instruct?
Magistral Medium is the stronger model overall, scoring 35.2 to 33.0 on the Noometry Index.
Is Magistral Medium or Phi 3 Medium 4k Instruct better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 32.9 in the Noometry coding category.
How many benchmarks do Magistral Medium and Phi 3 Medium 4k Instruct share?
17 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.