Model comparison
Claude Sonnet 4.6 vs Magistral Medium
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 35.2 on the Noometry Index. Magistral Medium costs 2.2× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Mistral AISummary
- They share 21 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 8 categories and Magistral Medium in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Sonnet 4.6 leads 46.1 to 8.6.
- The biggest single-benchmark swing is ARC-AGI-1: 86.5% for Claude Sonnet 4.6 and 6.1% for Magistral Medium.
- Magistral Medium is cheaper at $2 / $5 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
- Claude Sonnet 4.6 accepts more context: 1M tokens versus 262K.
- Magistral Medium has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4.6 | Magistral Medium | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 50.3 | 35.2 |
| Released | 2026-02-17 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | 1M | 262K |
| Max output | 128K | 16K |
| Input $ / M tokens | $3 | $2 |
| Output $ / M tokens | $15 | $5 |
| Results tracked | 57 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.3 (#67), Magistral Medium: 39.1 (#161)
| Benchmark | Claude Sonnet 4.6 | Magistral Medium |
|---|---|---|
| SciCode | 46.8% | 39.2% |
| LMArena Coding | 1504 | 1319 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| LMArena WebDev | 1522 | — |
| WeirdML | 66.1% | — |
| ALE-Bench | 1,327 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4.6: 39.1 (#28), Magistral Medium: —
| Benchmark | Claude Sonnet 4.6 | Magistral Medium |
|---|---|---|
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| LMArena Search | 1221 | — |
| Vending-Bench 2 | 7,204 | — |
Reasoning Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.1 (#45), Magistral Medium: 8.6 (#348)
| Benchmark | Claude Sonnet 4.6 | Magistral Medium |
|---|---|---|
| ARC-AGI-2 | 60.4% | 0% |
| ARC-AGI-1 | 86.5% | 6.1% |
| CritPt | 3.1% | 0.3% |
| LMArena Hard Prompts | 1484 | 1267 |
| Kagi LLM Benchmark | — | 16.2% |
| NYT Connections (extended) | 80.9% | — |
| Chess Puzzles | 13% | — |
| Thematic Generalization | 76.3% | — |
| Mystery Game Puzzles | 16% | — |
| DTBench | 89.9% | — |
| LMCA | 46.5% | — |
| Epoch Capabilities Index | 152.24 | — |
| ForecastBench | 62 | — |
Math Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 52.9 (#49), Magistral Medium: 35.1 (#189)
| Benchmark | Claude Sonnet 4.6 | Magistral Medium |
|---|---|---|
| LMArena Math | 1462 | 1250 |
| OTIS Mock AIME 2024-2025 | 85.8% | — |
| ProofBench | 45% | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |
Knowledge Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 51.7 (#65), Magistral Medium: 33.5 (#202)
| Benchmark | Claude Sonnet 4.6 | Magistral Medium |
|---|---|---|
| LMArena Expert | 1500 | 1223 |
| GPQA Diamond | 87.4% | — |
| SimpleQA Verified | 35.5% | — |
| Vectara Hallucination Rate | 10.6% | — |
Multimodal Not comparable
Claude Sonnet 4.6: 38.0 (#68), Magistral Medium: —
| Benchmark | Claude Sonnet 4.6 | Magistral Medium |
|---|---|---|
| LMArena Vision | 1283 | — |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |
Multilingual Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 54.4 (#41), Magistral Medium: 39.6 (#224)
| Benchmark | Claude Sonnet 4.6 | Magistral Medium |
|---|---|---|
| LMArena Non-English | 1440 | 1232 |
| LMArena Chinese | 1491 | 1227 |
| LMArena French | 1465 | 1267 |
| LMArena German | 1428 | 1248 |
| LMArena Japanese | 1420 | 1175 |
| LMArena Korean | 1411 | 1125 |
| LMArena Russian | 1440 | 1224 |
| LMArena Spanish | 1464 | 1271 |
Instruction Following Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 77.4 (#25), Magistral Medium: 66.0 (#211)
| Benchmark | Claude Sonnet 4.6 | Magistral Medium |
|---|---|---|
| LMArena Instruction Following | 1475 | 1254 |
Long Context Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 45.3 (#44), Magistral Medium: 39.3 (#183)
| Benchmark | Claude Sonnet 4.6 | Magistral Medium |
|---|---|---|
| LMArena Longer Query | 1479 | 1295 |
Writing & Preference Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 70.2 (#22), Magistral Medium: 46.3 (#219)
| Benchmark | Claude Sonnet 4.6 | Magistral Medium |
|---|---|---|
| LMArena Text | 1458 | 1255 |
| LMArena Creative Writing | 1435 | 1245 |
| LMArena Multi-Turn | 1464 | 1275 |
| EQ-Bench Creative Writing | 1810 | — |
| EQ-Bench 4 | 1207 | — |
Frequently asked questions
Is Claude Sonnet 4.6 better than Magistral Medium?
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 35.2 on the Noometry Index. Magistral Medium costs 2.2× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4.6 or Magistral Medium?
Magistral Medium is cheaper. It lists at $2 per million input tokens and $5 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.
Is Claude Sonnet 4.6 or Magistral Medium better for coding?
Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 39.1 in the Noometry coding category.
Which has the bigger context window?
Claude Sonnet 4.6 does, with 1M tokens against 262K.
How many benchmarks do Claude Sonnet 4.6 and Magistral Medium share?
21 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Magistral Medium has 22.