Model comparison
Claude 3 Opus vs Mistral Medium
Mistral Medium is the stronger model overall, scoring 36.3 to 29.5 on the Noometry Index.
Last verified . 24 shared benchmarks.
Mistral AISummary
- They share 24 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Mistral Medium in 10 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral Medium leads 28.1 to 14.8.
- The biggest single-benchmark swing is MATH Level 5: 37.5% for Claude 3 Opus and 81.6% for Mistral Medium.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Opus | Mistral Medium | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 29.5 | 36.3 |
| Released | 2024-02-29 | 2023-12-11 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 46 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Medium leads
Claude 3 Opus: 32.9 (#267), Mistral Medium: 34.2 (#243)
| Benchmark | Claude 3 Opus | Mistral Medium |
|---|---|---|
| WeirdML | 19.2% | 43.7% |
| LMArena Coding | 1264 | 1434 |
| FrontierCode | — | 8% |
| SciCode | — | 40.2% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 763.98 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Mistral Medium leads
Claude 3 Opus: 24.6 (#116), Mistral Medium: 28.3 (#90)
| Benchmark | Claude 3 Opus | Mistral Medium |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.7% |
| Cybench | 10% | — |
| METR Time Horizons | 29.5% | — |
Reasoning Mistral Medium leads
Claude 3 Opus: 14.6 (#324), Mistral Medium: 24.0 (#167)
| Benchmark | Claude 3 Opus | Mistral Medium |
|---|---|---|
| LMArena Hard Prompts | 1245 | 1426 |
| DTBench | 61.6% | 75.5% |
| LMCA | 17% | 26.1% |
| SimpleBench | 23.5% | — |
| Kagi LLM Benchmark | — | 50% |
| CritPt | — | 0% |
| Chess Puzzles | 5% | — |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| Surface Evolver Bench | — | 26.9% |
| Epoch Capabilities Index | 126.91 | — |
| ForecastBench | 58.4 | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Mistral Medium leads
Claude 3 Opus: 14.8 (#299), Mistral Medium: 28.1 (#245)
| Benchmark | Claude 3 Opus | Mistral Medium |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 32.2% |
| LMArena Math | 1273 | 1408 |
| MATH Level 5 | 37.5% | 81.6% |
| ProofBench | — | 9% |
| LiveBench Math | 43.6% | — |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Too close to call
Claude 3 Opus: 24.5 (#267), Mistral Medium: 25.0 (#265)
| Benchmark | Claude 3 Opus | Mistral Medium |
|---|---|---|
| GPQA Diamond | 47.2% | 59.5% |
| LMArena Expert | 1223 | 1408 |
| Humanity's Last Exam | — | 4.5% |
| SimpleQA Verified | 12.6% | — |
| Confabulations | 22.7% | — |
| Vectara Hallucination Rate | — | 22.7% |
| MMLU | 84.6% | — |
Multimodal Mistral Medium leads
Claude 3 Opus: 27.1 (#116), Mistral Medium: 35.3 (#88)
| Benchmark | Claude 3 Opus | Mistral Medium |
|---|---|---|
| LMArena Vision | 1023 | 1172 |
Multilingual Mistral Medium leads
Claude 3 Opus: 41.4 (#207), Mistral Medium: 52.1 (#91)
| Benchmark | Claude 3 Opus | Mistral Medium |
|---|---|---|
| LMArena Non-English | 1258 | 1408 |
| LMArena Chinese | 1248 | 1447 |
| LMArena French | 1275 | 1459 |
| LMArena German | 1258 | 1432 |
| LMArena Japanese | 1204 | 1378 |
| LMArena Korean | 1187 | 1380 |
| LMArena Russian | 1280 | 1411 |
| LMArena Spanish | 1246 | 1433 |
Instruction Following Mistral Medium leads
Claude 3 Opus: 64.1 (#228), Mistral Medium: 73.7 (#116)
| Benchmark | Claude 3 Opus | Mistral Medium |
|---|---|---|
| LMArena Instruction Following | 1248 | 1398 |
| LiveBench Instruction Following | 63.9% | — |
Long Context Mistral Medium leads
Claude 3 Opus: 38.2 (#202), Mistral Medium: 42.9 (#114)
| Benchmark | Claude 3 Opus | Mistral Medium |
|---|---|---|
| LMArena Longer Query | 1259 | 1406 |
Writing & Preference Mistral Medium leads
Claude 3 Opus: 47.2 (#213), Mistral Medium: 60.0 (#103)
| Benchmark | Claude 3 Opus | Mistral Medium |
|---|---|---|
| LMArena Text | 1262 | 1424 |
| LMArena Creative Writing | 1235 | 1391 |
| LMArena Multi-Turn | 1275 | 1418 |
| Short-Story Creative Writing | — | 77.3% |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Mistral Medium?
Mistral Medium is the stronger model overall, scoring 36.3 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Mistral Medium better for coding?
Mistral Medium scores higher on coding benchmarks: 34.2 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Mistral Medium share?
24 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Mistral Medium has 36.