Model comparison
Claude Opus 5 vs Mistral Medium
Claude Opus 5 is the stronger model overall, scoring 67.8 to 36.3 on the Noometry Index. Mistral Medium costs 3.3× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Last verified . 28 shared benchmarks.
Mistral AISummary
- They share 28 benchmarks with published results for both. Claude Opus 5 scores higher in 10 categories and Mistral Medium in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Opus 5 leads 86.2 to 28.1.
- The biggest single-benchmark swing is ProofBench: 99% for Claude Opus 5 and 9% for Mistral Medium.
- Mistral Medium is cheaper at $1.50 / $7.50 per million input/output tokens, against $5 / $25 for Claude Opus 5.
- Claude Opus 5 accepts more context: 1M tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Claude Opus 5 | Mistral Medium | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 67.8 | 36.3 |
| Released | 2026-07-24 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | 1M | 262K |
| Max output | 128K | 262K |
| Input $ / M tokens | $5 | $1.50 |
| Output $ / M tokens | $25 | $7.50 |
| Results tracked | 57 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5 leads
Claude Opus 5: 67.5 (#5), Mistral Medium: 34.2 (#243)
| Benchmark | Claude Opus 5 | Mistral Medium |
|---|---|---|
| FrontierCode | 53.4% | 8% |
| SciCode | 56.4% | 40.2% |
| WeirdML | 91.8% | 43.7% |
| LMArena Coding | 1534 | 1434 |
| ALE-Bench | 2,165 | 763.98 |
| DeepSWE | 73.6% | — |
| CursorBench | 46.6% | — |
| LMArena WebDev | 1691 | — |
| FrontierSWE | 52% | — |
Agentic & Tool Use Claude Opus 5 leads
Claude Opus 5: 55.6 (#1), Mistral Medium: 28.3 (#90)
| Benchmark | Claude Opus 5 | Mistral Medium |
|---|---|---|
| APEX-Agents | 65.8% | — |
| Berkeley Function Calling Leaderboard | — | 37.7% |
| OSWorld 2.0 | 31.4% | — |
| τ²-bench Banking | 48.7% | — |
| PostTrainBench | 35% | — |
| BALROG | 63.4% | — |
| GBAEval | 79.6% | — |
| GDP.pdf | 24% | — |
| Vending-Bench 2 | 11,182 | — |
Reasoning Claude Opus 5 leads
Claude Opus 5: 77.2 (#4), Mistral Medium: 24.0 (#167)
| Benchmark | Claude Opus 5 | Mistral Medium |
|---|---|---|
| CritPt | 29.1% | 0% |
| LMArena Hard Prompts | 1526 | 1426 |
| DTBench | 97.9% | 75.5% |
| LMCA | 64.5% | 26.1% |
| ARC-AGI-2 | 90.4% | — |
| SimpleBench | 80.6% | — |
| Kagi LLM Benchmark | — | 50% |
| NYT Connections (extended) | 94.3% | — |
| ARC-AGI-1 | 97.5% | — |
| Chess Puzzles | 42% | — |
| EBR-Bench | 45.7% | — |
| Mystery Game Puzzles | 59% | — |
| Surface Evolver Bench | — | 26.9% |
| Bench to the Future 3 | 0.12 | — |
| Epoch Capabilities Index | 162.78 | — |
Math Claude Opus 5 leads
Claude Opus 5: 86.2 (#8), Mistral Medium: 28.1 (#245)
| Benchmark | Claude Opus 5 | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 98.9% | 32.2% |
| ProofBench | 99% | 9% |
| LMArena Math | 1531 | 1408 |
| FrontierMath (Tiers 1-3) | 85.6% | — |
| FrontierMath Tier 4 | 73.2% | — |
| MATH Level 5 | — | 81.6% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Claude Opus 5 leads
Claude Opus 5: 66.8 (#9), Mistral Medium: 25.0 (#265)
| Benchmark | Claude Opus 5 | Mistral Medium |
|---|---|---|
| GPQA Diamond | 93.9% | 59.5% |
| LMArena Expert | 1557 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| SimpleQA Verified | 59.9% | — |
| Vectara Hallucination Rate | — | 22.7% |
Multimodal Claude Opus 5 leads
Claude Opus 5: 50.8 (#8), Mistral Medium: 35.3 (#88)
| Benchmark | Claude Opus 5 | Mistral Medium |
|---|---|---|
| LMArena Vision | 1319 | 1172 |
| Blueprint-Bench 2 | 30.4% | — |
| Furniture Assembly | 60.8% | — |
| LMArena Document | 1516 | — |
Multilingual Claude Opus 5 leads
Claude Opus 5: 58.8 (#4), Mistral Medium: 52.1 (#91)
| Benchmark | Claude Opus 5 | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1501 | 1408 |
| LMArena Chinese | 1574 | 1447 |
| LMArena French | 1519 | 1459 |
| LMArena German | 1524 | 1432 |
| LMArena Japanese | 1516 | 1378 |
| LMArena Korean | 1521 | 1380 |
| LMArena Russian | 1507 | 1411 |
| LMArena Spanish | 1519 | 1433 |
Instruction Following Claude Opus 5 leads
Claude Opus 5: 79.2 (#7), Mistral Medium: 73.7 (#116)
| Benchmark | Claude Opus 5 | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1517 | 1398 |
Long Context Claude Opus 5 leads
Claude Opus 5: 46.5 (#21), Mistral Medium: 42.9 (#114)
| Benchmark | Claude Opus 5 | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1515 | 1406 |
Writing & Preference Claude Opus 5 leads
Claude Opus 5: 79.2 (#1), Mistral Medium: 60.0 (#103)
| Benchmark | Claude Opus 5 | Mistral Medium |
|---|---|---|
| LMArena Text | 1507 | 1424 |
| LMArena Creative Writing | 1491 | 1391 |
| LMArena Multi-Turn | 1499 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| EQ-Bench Creative Writing | 2133 | — |
| EQ-Bench 4 | 1385 | — |
Frequently asked questions
Is Claude Opus 5 better than Mistral Medium?
Claude Opus 5 is the stronger model overall, scoring 67.8 to 36.3 on the Noometry Index. Mistral Medium costs 3.3× less per token, which makes it the better buy when Claude Opus 5's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 5 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 5 lists at $5 and $25.
Is Claude Opus 5 or Mistral Medium better for coding?
Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 5 does, with 1M tokens against 262K.
How many benchmarks do Claude Opus 5 and Mistral Medium share?
28 benchmarks have published results for both models. Claude Opus 5 has 57 scored results on Noometry and Mistral Medium has 36.