Model comparison
Magistral Medium vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 35.2 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
PerplexitySummary
- The widest gap is in reasoning, where Sonar leads 21.1 to 8.6.
- Sonar is cheaper at $1 / $1 per million input/output tokens, against $2 / $5 for Magistral Medium.
- Magistral Medium accepts more context: 262K tokens versus 128K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Magistral Medium | Sonar | |
|---|---|---|
| Provider | Mistral AI | Perplexity |
| Noometry Index | 35.2 | 38.5 |
| Released | 2025-03-17 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 262K | 128K |
| Max output | 16K | 4K |
| Input $ / M tokens | $2 | $1 |
| Output $ / M tokens | $5 | $1 |
| Results tracked | 22 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Magistral Medium leads
Magistral Medium: 39.1 (#161), Sonar: 35.7 (#221)
| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| SciCode | 39.2% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1319 | — |
Reasoning Sonar leads
Magistral Medium: 8.6 (#348), Sonar: 21.1 (#227)
| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 16.2% | — |
| ARC-AGI-1 | 6.1% | — |
| CritPt | 0.3% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1267 | — |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |
Math Magistral Medium leads
Magistral Medium: 35.1 (#189), Sonar: 33.7 (#200)
| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |
| LMArena Math | 1250 | — |
Knowledge Not comparable
Magistral Medium: 33.5 (#202), Sonar: —
| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| LMArena Expert | 1223 | — |
Multilingual Not comparable
Magistral Medium: 39.6 (#224), Sonar: —
| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| LMArena Non-English | 1232 | — |
| LMArena Chinese | 1227 | — |
| LMArena French | 1267 | — |
| LMArena German | 1248 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1125 | — |
| LMArena Russian | 1224 | — |
| LMArena Spanish | 1271 | — |
Instruction Following Sonar leads
Magistral Medium: 66.0 (#211), Sonar: 71.4 (#150)
| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1254 | — |
Long Context Not comparable
Magistral Medium: 39.3 (#183), Sonar: —
| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| LMArena Longer Query | 1295 | — |
Writing & Preference Sonar leads
Magistral Medium: 46.3 (#219), Sonar: 52.6 (#167)
| Benchmark | Magistral Medium | Sonar |
|---|---|---|
| LMArena Text | 1255 | — |
| LMArena Creative Writing | 1245 | — |
| LMArena Multi-Turn | 1275 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Magistral Medium better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 35.2 on the Noometry Index.
Which is cheaper, Magistral Medium or Sonar?
Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; Magistral Medium lists at $2 and $5.
Is Magistral Medium or Sonar better for coding?
Magistral Medium scores higher on coding benchmarks: 39.1 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 128K.
How many benchmarks do Magistral Medium and Sonar share?
0 benchmarks have published results for both models. Magistral Medium has 22 scored results on Noometry and Sonar has 7.