Model comparison
Magistral Medium vs Mistral 7B
Magistral Medium is the stronger model overall, scoring 35.2 to 23.0 on the Noometry Index. Mistral 7B costs 11× less per token, which makes it the better buy when Magistral Medium's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Mistral AISummary
- They share 16 benchmarks with published results for both. Magistral Medium scores higher in 7 categories and Mistral 7B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Magistral Medium leads 35.1 to 8.1.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 8K.
Side by side
| Magistral Medium | Mistral 7B | |
|---|---|---|
| Provider | Mistral AI | Mistral AI |
| Noometry Index | 35.2 | 23.0 |
| Released | 2025-03-17 | 2023-09-27 |
| Weights | Open | Open |
| Context window | 262K | 8K |
| Max output | 16K | 8K |
| Input $ / M tokens | $2 | $0.25 |
| Output $ / M tokens | $5 | $0.25 |
| Results tracked | 22 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Magistral Medium: 39.1 (#161), Mistral 7B: 26.4 (#326)
| Benchmark | Magistral Medium | Mistral 7B |
|---|---|---|
| LMArena Coding | 1319 | 1082 |
| SciCode | 39.2% | — |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Reasoning Mistral 7B leads
Magistral Medium: 8.6 (#348), Mistral 7B: 13.1 (#336)
| Benchmark | Magistral Medium | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1067 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| Epoch Capabilities Index | — | 112.21 |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math Magistral Medium leads
Magistral Medium: 35.1 (#189), Mistral 7B: 8.1 (#325)
| Benchmark | Magistral Medium | Mistral 7B |
|---|---|---|
| LMArena Math | 1250 | 1085 |
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| MATH Level 5 | — | 3.7% |
| GSM8K | — | 54.4% |
Knowledge Magistral Medium leads
Magistral Medium: 33.5 (#202), Mistral 7B: 7.4 (#311)
| Benchmark | Magistral Medium | Mistral 7B |
|---|---|---|
| LMArena Expert | 1223 | 1036 |
| GPQA Diamond | — | 15.2% |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multilingual Magistral Medium leads
Magistral Medium: 39.6 (#224), Mistral 7B: 25.8 (#283)
| Benchmark | Magistral Medium | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1232 | 1012 |
| LMArena Chinese | 1227 | 1009 |
| LMArena French | 1267 | 1037 |
| LMArena German | 1248 | 987 |
| LMArena Japanese | 1175 | 878 |
| LMArena Russian | 1224 | 1018 |
| LMArena Spanish | 1271 | 1026 |
| LMArena Korean | 1125 | — |
Instruction Following Magistral Medium leads
Magistral Medium: 66.0 (#211), Mistral 7B: 54.2 (#280)
| Benchmark | Magistral Medium | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1254 | 1060 |
Long Context Magistral Medium leads
Magistral Medium: 39.3 (#183), Mistral 7B: 32.2 (#271)
| Benchmark | Magistral Medium | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1295 | 1060 |
Writing & Preference Magistral Medium leads
Magistral Medium: 46.3 (#219), Mistral 7B: 30.7 (#286)
| Benchmark | Magistral Medium | Mistral 7B |
|---|---|---|
| LMArena Text | 1255 | 1090 |
| LMArena Creative Writing | 1245 | 1068 |
| LMArena Multi-Turn | 1275 | 1062 |
Frequently asked questions
Is Magistral Medium better than Mistral 7B?
Magistral Medium is the stronger model overall, scoring 35.2 to 23.0 on the Noometry Index. Mistral 7B costs 11× 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 Mistral 7B?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or Mistral 7B better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 8K.
How many benchmarks do Magistral Medium and Mistral 7B share?
16 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Mistral 7B has 37.