Model comparison
Mistral Medium vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 36.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
PerplexitySummary
- The widest gap is in writing & preference, where Mistral Medium leads 60.0 to 52.6.
- Sonar is cheaper at $1 / $1 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Mistral Medium accepts more context: 262K tokens versus 128K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Mistral Medium | Sonar | |
|---|---|---|
| Provider | Mistral AI | Perplexity |
| Noometry Index | 36.3 | 38.5 |
| Released | 2023-12-11 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 262K | 128K |
| Max output | 262K | 4K |
| Input $ / M tokens | $1.50 | $1 |
| Output $ / M tokens | $7.50 | $1 |
| Results tracked | 36 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Mistral Medium: 34.2 (#243), Sonar: 35.7 (#221)
| Benchmark | Mistral Medium | Sonar |
|---|---|---|
| FrontierCode | 8% | — |
| SciCode | 40.2% | — |
| WeirdML | 43.7% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1434 | — |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Not comparable
Mistral Medium: 28.3 (#90), Sonar: —
| Benchmark | Mistral Medium | Sonar |
|---|---|---|
| Berkeley Function Calling Leaderboard | 37.7% | — |
Reasoning Mistral Medium leads
Mistral Medium: 24.0 (#167), Sonar: 21.1 (#227)
| Benchmark | Mistral Medium | Sonar |
|---|---|---|
| Kagi LLM Benchmark | 50% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1426 | — |
| DTBench | 75.5% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 26.1% | — |
| Surface Evolver Bench | 26.9% | — |
| LiveBench | — | 46.9% |
Math Sonar leads
Mistral Medium: 28.1 (#245), Sonar: 33.7 (#200)
| Benchmark | Mistral Medium | Sonar |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 32.2% | — |
| ProofBench | 9% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1408 | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Not comparable
Mistral Medium: 25.0 (#265), Sonar: —
| Benchmark | Mistral Medium | Sonar |
|---|---|---|
| GPQA Diamond | 59.5% | — |
| Humanity's Last Exam | 4.5% | — |
| Vectara Hallucination Rate | 22.7% | — |
| LMArena Expert | 1408 | — |
Multimodal Not comparable
Mistral Medium: 35.3 (#88), Sonar: —
| Benchmark | Mistral Medium | Sonar |
|---|---|---|
| LMArena Vision | 1172 | — |
Multilingual Not comparable
Mistral Medium: 52.1 (#91), Sonar: —
| Benchmark | Mistral Medium | Sonar |
|---|---|---|
| LMArena Non-English | 1408 | — |
| LMArena Chinese | 1447 | — |
| LMArena French | 1459 | — |
| LMArena German | 1432 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1380 | — |
| LMArena Russian | 1411 | — |
| LMArena Spanish | 1433 | — |
Instruction Following Mistral Medium leads
Mistral Medium: 73.7 (#116), Sonar: 71.4 (#150)
| Benchmark | Mistral Medium | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1398 | — |
Long Context Not comparable
Mistral Medium: 42.9 (#114), Sonar: —
| Benchmark | Mistral Medium | Sonar |
|---|---|---|
| LMArena Longer Query | 1406 | — |
Writing & Preference Mistral Medium leads
Mistral Medium: 60.0 (#103), Sonar: 52.6 (#167)
| Benchmark | Mistral Medium | Sonar |
|---|---|---|
| LMArena Text | 1424 | — |
| LMArena Creative Writing | 1391 | — |
| Short-Story Creative Writing | 77.3% | — |
| LMArena Multi-Turn | 1418 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Mistral Medium better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 36.3 on the Noometry Index.
Which is cheaper, Mistral Medium or Sonar?
Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.7 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 128K.
How many benchmarks do Mistral Medium and Sonar share?
0 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Sonar has 7.