Model comparison
Claude Opus 4 vs Mistral Medium
Claude Opus 4 is the stronger model overall, scoring 43.1 to 36.3 on the Noometry Index. Mistral Medium costs 10× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Last verified . 30 shared benchmarks.
Mistral AISummary
- They share 30 benchmarks with published results for both. Claude Opus 4 scores higher in 7 categories and Mistral Medium in 3 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Claude Opus 4 leads 44.0 to 25.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 64.4% for Claude Opus 4 and 32.2% for Mistral Medium.
- Mistral Medium is cheaper at $1.50 / $7.50 per million input/output tokens, against $15 / $75 for Claude Opus 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 Opus 4 | Mistral Medium | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 43.1 | 36.3 |
| Released | 2025-05-22 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 32K | 262K |
| Input $ / M tokens | $15 | $1.50 |
| Output $ / M tokens | $75 | $7.50 |
| Results tracked | 56 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 4 leads
Claude Opus 4: 47.2 (#62), Mistral Medium: 34.2 (#243)
| Benchmark | Claude Opus 4 | Mistral Medium |
|---|---|---|
| WeirdML | 43.7% | 43.7% |
| LMArena Coding | 1442 | 1434 |
| SWE-bench Verified | 70.7% | — |
| FrontierCode | — | 8% |
| SWE-bench Verified (bash only) | 67.6% | — |
| Aider Polyglot | 72% | — |
| SciCode | — | 40.2% |
| GSO | 6.9% | — |
| ALE-Bench | — | 763.98 |
| AlgoTune | 1.33 | — |
Agentic & Tool Use Claude Opus 4 leads
Claude Opus 4: 34.8 (#42), Mistral Medium: 28.3 (#90)
| Benchmark | Claude Opus 4 | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
| Cybench | 38% | — |
| DeepResearch Bench | 46.8% | — |
| LMArena Search | 1127 | — |
| METR Time Horizons | 63.9% | — |
Reasoning Claude Opus 4 leads
Claude Opus 4: 27.3 (#121), Mistral Medium: 24.0 (#167)
| Benchmark | Claude Opus 4 | Mistral Medium |
|---|---|---|
| Kagi LLM Benchmark | 74.3% | 50% |
| CritPt | 0.3% | 0% |
| LMArena Hard Prompts | 1399 | 1426 |
| DTBench | 81.6% | 75.5% |
| LMCA | 37.4% | 26.1% |
| ARC-AGI-2 | 8.6% | — |
| SimpleBench | 58.8% | — |
| ARC-AGI-1 | 35.7% | — |
| EnigmaEval | 5.6% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 142.67 | — |
| ForecastBench | 61.1 | — |
Math Claude Opus 4 leads
Claude Opus 4: 42.0 (#86), Mistral Medium: 28.1 (#245)
| Benchmark | Claude Opus 4 | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 64.4% | 32.2% |
| LMArena Math | 1390 | 1408 |
| MATH Level 5 | 85% | 81.6% |
| FrontierMath (Feb 2025 set) | 4.5% | 0.3% |
| ProofBench | — | 9% |
| Omni-MATH | 61.6% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Claude Opus 4 leads
Claude Opus 4: 44.0 (#88), Mistral Medium: 25.0 (#265)
| Benchmark | Claude Opus 4 | Mistral Medium |
|---|---|---|
| GPQA Diamond | 76.3% | 59.5% |
| Humanity's Last Exam | 10.7% | 4.5% |
| Vectara Hallucination Rate | 12% | 22.7% |
| LMArena Expert | 1386 | 1408 |
| MMLU-Pro | 87.5% | — |
| Confabulations | 15.9% | — |
| GPQA (HELM) | 70.8% | — |
Multimodal Mistral Medium leads
Claude Opus 4: 31.5 (#106), Mistral Medium: 35.3 (#88)
| Benchmark | Claude Opus 4 | Mistral Medium |
|---|---|---|
| LMArena Vision | 1192 | 1172 |
| GeoBench | 49% | — |
| VPCT | 38% | — |
Multilingual Mistral Medium leads
Claude Opus 4: 48.8 (#138), Mistral Medium: 52.1 (#91)
| Benchmark | Claude Opus 4 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1362 | 1408 |
| LMArena Chinese | 1386 | 1447 |
| LMArena French | 1372 | 1459 |
| LMArena German | 1391 | 1432 |
| LMArena Japanese | 1331 | 1378 |
| LMArena Korean | 1321 | 1380 |
| LMArena Russian | 1392 | 1411 |
| LMArena Spanish | 1389 | 1433 |
Instruction Following Claude Opus 4 leads
Claude Opus 4: 77.1 (#28), Mistral Medium: 73.7 (#116)
| Benchmark | Claude Opus 4 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1406 | 1398 |
| IFEval | 91.8% | — |
Long Context Mistral Medium leads
Claude Opus 4: 39.6 (#172), Mistral Medium: 42.9 (#114)
| Benchmark | Claude Opus 4 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1422 | 1406 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Claude Opus 4 leads
Claude Opus 4: 61.2 (#89), Mistral Medium: 60.0 (#103)
| Benchmark | Claude Opus 4 | Mistral Medium |
|---|---|---|
| LMArena Text | 1377 | 1424 |
| LMArena Creative Writing | 1387 | 1391 |
| Short-Story Creative Writing | 83.6% | 77.3% |
| LMArena Multi-Turn | 1396 | 1418 |
| EQ-Bench Creative Writing | 1580 | — |
| WildBench | 85.2% | — |
Frequently asked questions
Is Claude Opus 4 better than Mistral Medium?
Claude Opus 4 is the stronger model overall, scoring 43.1 to 36.3 on the Noometry Index. Mistral Medium costs 10× less per token, which makes it the better buy when Claude Opus 4's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 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 Opus 4 lists at $15 and $75.
Is Claude Opus 4 or Mistral Medium better for coding?
Claude Opus 4 scores higher on coding benchmarks: 47.2 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 Opus 4 and Mistral Medium share?
30 benchmarks have published results for both models. Claude Opus 4 has 56 scored results on Noometry and Mistral Medium has 36.