Model comparison
Magistral Medium vs Ministral 8B
Magistral Medium is the stronger model overall, scoring 35.2 to 28.2 on the Noometry Index. Ministral 8B costs 18× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
Mistral AISummary
- They share 12 benchmarks with published results for both. Magistral Medium scores higher in 7 categories and Ministral 8B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Magistral Medium leads 33.5 to 12.6.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $2 / $5 for Magistral Medium.
Side by side
| Magistral Medium | Ministral 8B | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 35.2 | 28.2 |
| Released | 2025-03-17 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 16K | 262K |
| Input $ / M tokens | $2 | $0.15 |
| Output $ / M tokens | $5 | $0.15 |
| 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), Ministral 8B: 35.0 (#230)
| Benchmark | Magistral Medium | Ministral 8B |
|---|---|---|
| LMArena Coding | 1319 | 1202 |
| SciCode | 39.2% | — |
Agentic & Tool Use Not comparable
Magistral Medium: —, Ministral 8B: 16.4 (#148)
| Benchmark | Magistral Medium | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Ministral 8B leads
Magistral Medium: 8.6 (#348), Ministral 8B: 18.4 (#281)
| Benchmark | Magistral Medium | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1191 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| DTBench | — | 45.7% |
Math Magistral Medium leads
Magistral Medium: 35.1 (#189), Ministral 8B: 25.7 (#267)
| Benchmark | Magistral Medium | Ministral 8B |
|---|---|---|
| LMArena Math | 1250 | 1188 |
| MATH Level 5 | — | 14.9% |
Knowledge Magistral Medium leads
Magistral Medium: 33.5 (#202), Ministral 8B: 12.6 (#297)
| Benchmark | Magistral Medium | Ministral 8B |
|---|---|---|
| LMArena Expert | 1223 | 1170 |
| GPQA Diamond | — | 27.1% |
| Vectara Hallucination Rate | — | 7.4% |
Multilingual Magistral Medium leads
Magistral Medium: 39.6 (#224), Ministral 8B: 35.1 (#247)
| Benchmark | Magistral Medium | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1232 | 1165 |
| LMArena Chinese | 1227 | 1193 |
| LMArena Russian | 1224 | 1195 |
| LMArena French | 1267 | — |
| LMArena German | 1248 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1125 | — |
| LMArena Spanish | 1271 | — |
Instruction Following Magistral Medium leads
Magistral Medium: 66.0 (#211), Ministral 8B: 60.5 (#250)
| Benchmark | Magistral Medium | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1161 |
Long Context Magistral Medium leads
Magistral Medium: 39.3 (#183), Ministral 8B: 36.7 (#227)
| Benchmark | Magistral Medium | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1295 | 1212 |
Writing & Preference Magistral Medium leads
Magistral Medium: 46.3 (#219), Ministral 8B: 39.6 (#246)
| Benchmark | Magistral Medium | Ministral 8B |
|---|---|---|
| LMArena Text | 1255 | 1191 |
| LMArena Creative Writing | 1245 | 1175 |
| LMArena Multi-Turn | 1275 | 1166 |
Frequently asked questions
Is Magistral Medium better than Ministral 8B?
Magistral Medium is the stronger model overall, scoring 35.2 to 28.2 on the Noometry Index. Ministral 8B costs 18× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Which is cheaper, Magistral Medium or Ministral 8B?
Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or Ministral 8B better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 35.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Magistral Medium and Ministral 8B share?
12 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Ministral 8B has 17.