Model comparison
Claude Sonnet 4 vs Magistral Medium
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 35.2 on the Noometry Index. Magistral Medium costs 2.2× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. Claude Sonnet 4 scores higher in 7 categories and Magistral Medium in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Sonnet 4 leads 22.9 to 8.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 73% for Claude Sonnet 4 and 16.2% for Magistral Medium.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Magistral Medium accepts more context: 262K tokens versus 200K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | Magistral Medium | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 40.8 | 35.2 |
| Released | 2025-05-22 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 64K | 16K |
| Input $ / M tokens | $3 | $2 |
| Output $ / M tokens | $15 | $5 |
| Results tracked | 58 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4 leads
Claude Sonnet 4: 43.5 (#88), Magistral Medium: 39.1 (#161)
| Benchmark | Claude Sonnet 4 | Magistral Medium |
|---|---|---|
| SciCode | 40% | 39.2% |
| LMArena Coding | 1414 | 1319 |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| GSO | 4.9% | — |
| WeirdML | 46.1% | — |
| ALE-Bench | 655.35 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4: 38.5 (#31), Magistral Medium: —
| Benchmark | Claude Sonnet 4 | Magistral Medium |
|---|---|---|
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Claude Sonnet 4 leads
Claude Sonnet 4: 22.9 (#187), Magistral Medium: 8.6 (#348)
| Benchmark | Claude Sonnet 4 | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 5.9% | 0% |
| Kagi LLM Benchmark | 73% | 16.2% |
| ARC-AGI-1 | 40% | 6.1% |
| CritPt | 0.3% | 0.3% |
| LMArena Hard Prompts | 1372 | 1267 |
| SimpleBench | 45.5% | — |
| EnigmaEval | 3.1% | — |
| DTBench | 77.1% | — |
| LMCA | 29% | — |
| Epoch Capabilities Index | 141.69 | — |
| ForecastBench | 60.2 | — |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), Magistral Medium: 35.1 (#189)
| Benchmark | Claude Sonnet 4 | Magistral Medium |
|---|---|---|
| LMArena Math | 1375 | 1250 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| Omni-MATH | 60.2% | — |
| MATH Level 5 | 84.4% | — |
| FrontierMath (Feb 2025 set) | 4.1% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), Magistral Medium: 33.5 (#202)
| Benchmark | Claude Sonnet 4 | Magistral Medium |
|---|---|---|
| LMArena Expert | 1372 | 1223 |
| GPQA Diamond | 79.2% | — |
| Humanity's Last Exam | 7.8% | — |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| Vectara Hallucination Rate | 10.3% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Not comparable
Claude Sonnet 4: 26.2 (#121), Magistral Medium: —
| Benchmark | Claude Sonnet 4 | Magistral Medium |
|---|---|---|
| LMArena Vision | 1191 | — |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Claude Sonnet 4 leads
Claude Sonnet 4: 46.7 (#156), Magistral Medium: 39.6 (#224)
| Benchmark | Claude Sonnet 4 | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1333 | 1232 |
| LMArena Chinese | 1350 | 1227 |
| LMArena French | 1363 | 1267 |
| LMArena German | 1331 | 1248 |
| LMArena Japanese | 1302 | 1175 |
| LMArena Korean | 1291 | 1125 |
| LMArena Russian | 1355 | 1224 |
| LMArena Spanish | 1357 | 1271 |
Instruction Following Claude Sonnet 4 leads
Claude Sonnet 4: 71.7 (#145), Magistral Medium: 66.0 (#211)
| Benchmark | Claude Sonnet 4 | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1376 | 1254 |
| IFEval | 84% | — |
Long Context Magistral Medium leads
Claude Sonnet 4: 33.7 (#259), Magistral Medium: 39.3 (#183)
| Benchmark | Claude Sonnet 4 | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1398 | 1295 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Claude Sonnet 4 leads
Claude Sonnet 4: 57.1 (#132), Magistral Medium: 46.3 (#219)
| Benchmark | Claude Sonnet 4 | Magistral Medium |
|---|---|---|
| LMArena Text | 1351 | 1255 |
| LMArena Creative Writing | 1345 | 1245 |
| LMArena Multi-Turn | 1376 | 1275 |
| Short-Story Creative Writing | 81.4% | — |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than Magistral Medium?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 35.2 on the Noometry Index. Magistral Medium costs 2.2× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4 or Magistral Medium?
Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or Magistral Medium better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
Magistral Medium does, with 262K tokens against 200K.
How many benchmarks do Claude Sonnet 4 and Magistral Medium share?
22 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Magistral Medium has 22.