Model comparison
Claude Sonnet 4 vs Mistral Medium
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 36.3 on the Noometry Index. Mistral Medium costs 2.0× less per token, which makes it the better buy when Claude Sonnet 4's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
Mistral AISummary
- They share 32 benchmarks with published results for both. Claude Sonnet 4 scores higher in 4 categories and Mistral Medium in 6 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Sonnet 4 leads 41.8 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for Claude Sonnet 4 and 32.2% for Mistral Medium.
- Mistral Medium is cheaper at $1.50 / $7.50 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.
- Mistral Medium accepts more context: 262K tokens versus 200K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Claude Sonnet 4 | Mistral Medium | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 40.8 | 36.3 |
| Released | 2025-05-22 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 64K | 262K |
| Input $ / M tokens | $3 | $1.50 |
| Output $ / M tokens | $15 | $7.50 |
| Results tracked | 58 | 36 |
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), Mistral Medium: 34.2 (#243)
| Benchmark | Claude Sonnet 4 | Mistral Medium |
|---|---|---|
| SciCode | 40% | 40.2% |
| WeirdML | 46.1% | 43.7% |
| LMArena Coding | 1414 | 1434 |
| ALE-Bench | 655.35 | 763.98 |
| FrontierCode | — | 8% |
| SWE-bench Verified (bash only) | 64.9% | — |
| Aider Polyglot | 61.3% | — |
| GSO | 4.9% | — |
Agentic & Tool Use Claude Sonnet 4 leads
Claude Sonnet 4: 38.5 (#31), Mistral Medium: 28.3 (#90)
| Benchmark | Claude Sonnet 4 | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
| TheAgentCompany | 33.1% | — |
| Cybench | 35% | — |
| DeepResearch Bench | 46.6% | — |
| OSWorld | 43.9% | — |
| METR Time Horizons | 62% | — |
Reasoning Mistral Medium leads
Claude Sonnet 4: 22.9 (#187), Mistral Medium: 24.0 (#167)
| Benchmark | Claude Sonnet 4 | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 73% | 50% |
| CritPt | 0.3% | 0% |
| LMArena Hard Prompts | 1372 | 1426 |
| DTBench | 77.1% | 75.5% |
| LMCA | 29% | 26.1% |
| ARC-AGI-2 | 5.9% | — |
| SimpleBench | 45.5% | — |
| ARC-AGI-1 | 40% | — |
| EnigmaEval | 3.1% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 141.69 | — |
| ForecastBench | 60.2 | — |
Math Claude Sonnet 4 leads
Claude Sonnet 4: 43.3 (#80), Mistral Medium: 28.1 (#245)
| Benchmark | Claude Sonnet 4 | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 32.2% |
| LMArena Math | 1375 | 1408 |
| MATH Level 5 | 84.4% | 81.6% |
| FrontierMath (Feb 2025 set) | 4.1% | 0.3% |
| ProofBench | — | 9% |
| Omni-MATH | 60.2% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Claude Sonnet 4 leads
Claude Sonnet 4: 41.8 (#108), Mistral Medium: 25.0 (#265)
| Benchmark | Claude Sonnet 4 | Mistral Medium |
|---|---|---|
| GPQA Diamond | 79.2% | 59.5% |
| Humanity's Last Exam | 7.8% | 4.5% |
| Vectara Hallucination Rate | 10.3% | 22.7% |
| LMArena Expert | 1372 | 1408 |
| MMLU-Pro | 84.3% | — |
| Confabulations | 13.2% | — |
| GPQA (HELM) | 70.6% | — |
Multimodal Mistral Medium leads
Claude Sonnet 4: 26.2 (#121), Mistral Medium: 35.3 (#88)
| Benchmark | Claude Sonnet 4 | Mistral Medium |
|---|---|---|
| LMArena Vision | 1191 | 1172 |
| GeoBench | 37% | — |
| VPCT | 34% | — |
| MindCube | 44.8% | — |
Multilingual Mistral Medium leads
Claude Sonnet 4: 46.7 (#156), Mistral Medium: 52.1 (#91)
| Benchmark | Claude Sonnet 4 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1333 | 1408 |
| LMArena Chinese | 1350 | 1447 |
| LMArena French | 1363 | 1459 |
| LMArena German | 1331 | 1432 |
| LMArena Japanese | 1302 | 1378 |
| LMArena Korean | 1291 | 1380 |
| LMArena Russian | 1355 | 1411 |
| LMArena Spanish | 1357 | 1433 |
Instruction Following Mistral Medium leads
Claude Sonnet 4: 71.7 (#145), Mistral Medium: 73.7 (#116)
| Benchmark | Claude Sonnet 4 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1376 | 1398 |
| IFEval | 84% | — |
Long Context Mistral Medium leads
Claude Sonnet 4: 33.7 (#259), Mistral Medium: 42.9 (#114)
| Benchmark | Claude Sonnet 4 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1398 | 1406 |
| Fiction.LiveBench | 46.9% | — |
Writing & Preference Mistral Medium leads
Claude Sonnet 4: 57.1 (#132), Mistral Medium: 60.0 (#103)
| Benchmark | Claude Sonnet 4 | Mistral Medium |
|---|---|---|
| LMArena Text | 1351 | 1424 |
| LMArena Creative Writing | 1345 | 1391 |
| Short-Story Creative Writing | 81.4% | 77.3% |
| LMArena Multi-Turn | 1376 | 1418 |
| EQ-Bench Creative Writing | 1483 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is Claude Sonnet 4 better than Mistral Medium?
Claude Sonnet 4 is the stronger model overall, scoring 40.8 to 36.3 on the Noometry Index. Mistral Medium costs 2.0× 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 Mistral Medium?
Mistral Medium is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; Claude Sonnet 4 lists at $3 and $15.
Is Claude Sonnet 4 or Mistral Medium better for coding?
Claude Sonnet 4 scores higher on coding benchmarks: 43.5 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Mistral Medium does, with 262K tokens against 200K.
How many benchmarks do Claude Sonnet 4 and Mistral Medium share?
32 benchmarks have published results for both models. Claude Sonnet 4 has 58 scored results on Noometry and Mistral Medium has 36.