Model comparison
Magistral Medium vs Step 3
Step 3 is the stronger model overall, scoring 39.9 to 34.8 on the Noometry Index.
Last verified . 16 shared benchmarks.
Mistral AI
StepFunSummary
- They share 16 benchmarks with published results for both. Magistral Medium scores higher in 0 categories and Step 3 in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3 leads 27.6 to 8.7.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 16.2% for Magistral Medium and 62.3% for Step 3.
Side by side
| Magistral Medium | Step 3 | |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 34.8 | 39.9 |
| Released | 2025-03-17 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| 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 Too close to call
Magistral Medium: 38.6 (#161), Step 3: 39.5 (#144)
| Benchmark | Magistral Medium | Step 3 |
|---|---|---|
| LMArena Coding | 1319 | 1367 |
| SciCode | 39.2% | — |
Reasoning Step 3 leads
Magistral Medium: 8.7 (#342), Step 3: 27.6 (#102)
| Benchmark | Magistral Medium | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 16.2% | 62.3% |
| LMArena Hard Prompts | 1267 | 1355 |
| ARC-AGI-2 | 0% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
Math Step 3 leads
Magistral Medium: 32.4 (#187), Step 3: 34.9 (#148)
| Benchmark | Magistral Medium | Step 3 |
|---|---|---|
| LMArena Math | 1249 | 1366 |
Knowledge Step 3 leads
Magistral Medium: 32.9 (#199), Step 3: 36.2 (#161)
| Benchmark | Magistral Medium | Step 3 |
|---|---|---|
| LMArena Expert | 1222 | 1333 |
Multimodal Not comparable
Magistral Medium: —, Step 3: 34.9 (#81)
| Benchmark | Magistral Medium | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual Step 3 leads
Magistral Medium: 39.8 (#219), Step 3: 46.5 (#154)
| Benchmark | Magistral Medium | Step 3 |
|---|---|---|
| LMArena Non-English | 1232 | 1327 |
| LMArena Chinese | 1225 | 1396 |
| LMArena German | 1248 | 1371 |
| LMArena Korean | 1125 | 1271 |
| LMArena Russian | 1224 | 1331 |
| LMArena Spanish | 1269 | 1372 |
| LMArena French | 1268 | — |
| LMArena Japanese | 1176 | — |
Instruction Following Step 3 leads
Magistral Medium: 66.2 (#207), Step 3: 70.6 (#159)
| Benchmark | Magistral Medium | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1254 | 1332 |
Long Context Too close to call
Magistral Medium: 39.3 (#178), Step 3: 40.3 (#152)
| Benchmark | Magistral Medium | Step 3 |
|---|---|---|
| LMArena Longer Query | 1295 | 1326 |
Writing & Preference Step 3 leads
Magistral Medium: 46.5 (#214), Step 3: 54.5 (#146)
| Benchmark | Magistral Medium | Step 3 |
|---|---|---|
| LMArena Text | 1255 | 1351 |
| LMArena Creative Writing | 1245 | 1322 |
| LMArena Multi-Turn | 1275 | 1340 |
Frequently asked questions
Is Magistral Medium better than Step 3?
Step 3 is the stronger model overall, scoring 39.9 to 34.8 on the Noometry Index.
Is Magistral Medium or Step 3 better for coding?
They score almost the same on coding (38.6 vs 39.5); test both on your own repository before choosing.
How many benchmarks do Magistral Medium and Step 3 share?
16 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Step 3 has 17.