Model comparison
Claude 3 Opus vs Mistral Large
Mistral Large is the stronger model overall, scoring 31.9 to 29.5 on the Noometry Index.
Last verified . 38 shared benchmarks.
Mistral AISummary
- They share 38 benchmarks with published results for both. Claude 3 Opus scores higher in 2 categories and Mistral Large in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude 3 Opus leads 47.2 to 40.7.
- The biggest single-benchmark swing is BigCodeBench Complete: 57.4% for Claude 3 Opus and 38.3% for Mistral Large.
- Mistral Large has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Opus | Mistral Large | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 29.5 | 31.9 |
| Released | 2024-02-29 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 46 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Large leads
Claude 3 Opus: 32.9 (#267), Mistral Large: 34.3 (#240)
| Benchmark | Claude 3 Opus | Mistral Large |
|---|---|---|
| BigCodeBench Instruct | 45.5% | 30% |
| LiveBench Coding | 38.6% | 47.1% |
| LMArena Coding | 1264 | 1277 |
| BigCodeBench Complete | 57.4% | 38.3% |
| HumanEval+ | 77.4% | 62.2% |
| MBPP+ | 73.3% | 59.5% |
| SciCode | — | 36.2% |
| WeirdML | 19.2% | — |
| ALE-Bench | — | 264.7 |
Agentic & Tool Use Mistral Large leads
Claude 3 Opus: 24.6 (#116), Mistral Large: 28.6 (#89)
| Benchmark | Claude 3 Opus | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |
| Cybench | 10% | — |
| METR Time Horizons | 29.5% | — |
Reasoning Mistral Large leads
Claude 3 Opus: 14.6 (#324), Mistral Large: 15.8 (#310)
| Benchmark | Claude 3 Opus | Mistral Large |
|---|---|---|
| SimpleBench | 23.5% | 22.5% |
| LiveBench Reasoning | 40.6% | 43.5% |
| LMArena Hard Prompts | 1245 | 1257 |
| DTBench | 61.6% | 65.1% |
| LiveBench Data Analysis | 57.9% | 50.1% |
| LMCA | 17% | 16.7% |
| Epoch Capabilities Index | 126.91 | 128.52 |
| ForecastBench | 58.4 | 57.1 |
| LiveBench | 49.2% | 48.4% |
| CritPt | — | 0% |
| Chess Puzzles | 5% | — |
| EnigmaEval | 0.8% | — |
| WinoGrande | 88.5% | — |
Math Mistral Large leads
Claude 3 Opus: 14.8 (#299), Mistral Large: 18.2 (#291)
| Benchmark | Claude 3 Opus | Mistral Large |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 8.5% |
| LiveBench Math | 43.6% | 42.5% |
| LMArena Math | 1273 | 1262 |
| MATH Level 5 | 37.5% | 50.3% |
| Omni-MATH | — | 28.1% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge Mistral Large leads
Claude 3 Opus: 24.5 (#267), Mistral Large: 30.1 (#230)
| Benchmark | Claude 3 Opus | Mistral Large |
|---|---|---|
| GPQA Diamond | 47.2% | 51.3% |
| Confabulations | 22.7% | 21.4% |
| LMArena Expert | 1223 | 1232 |
| MMLU | 84.6% | 80% |
| SimpleQA Verified | 12.6% | — |
| MMLU-Pro | — | 59.9% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
Multimodal Not comparable
Claude 3 Opus: 27.1 (#116), Mistral Large: —
| Benchmark | Claude 3 Opus | Mistral Large |
|---|---|---|
| LMArena Vision | 1023 | — |
Multilingual Claude 3 Opus leads
Claude 3 Opus: 41.4 (#207), Mistral Large: 40.0 (#219)
| Benchmark | Claude 3 Opus | Mistral Large |
|---|---|---|
| LMArena Non-English | 1258 | 1237 |
| LMArena Chinese | 1248 | 1240 |
| LMArena French | 1275 | 1325 |
| LMArena German | 1258 | 1254 |
| LMArena Japanese | 1204 | 1188 |
| LMArena Korean | 1187 | 1202 |
| LMArena Russian | 1280 | 1257 |
| LMArena Spanish | 1246 | 1268 |
Instruction Following Mistral Large leads
Claude 3 Opus: 64.1 (#228), Mistral Large: 67.9 (#191)
| Benchmark | Claude 3 Opus | Mistral Large |
|---|---|---|
| LiveBench Instruction Following | 63.9% | 67.9% |
| LMArena Instruction Following | 1248 | 1249 |
| IFEval | — | 87.7% |
Long Context Too close to call
Claude 3 Opus: 38.2 (#202), Mistral Large: 38.3 (#199)
| Benchmark | Claude 3 Opus | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1259 | 1261 |
Writing & Preference Claude 3 Opus leads
Claude 3 Opus: 47.2 (#213), Mistral Large: 40.7 (#242)
| Benchmark | Claude 3 Opus | Mistral Large |
|---|---|---|
| LMArena Text | 1262 | 1266 |
| LMArena Creative Writing | 1235 | 1243 |
| LMArena Multi-Turn | 1275 | 1260 |
| LiveBench Language | 50.4% | 39.4% |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
Frequently asked questions
Is Claude 3 Opus better than Mistral Large?
Mistral Large is the stronger model overall, scoring 31.9 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Mistral Large better for coding?
Mistral Large scores higher on coding benchmarks: 34.3 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Mistral Large share?
38 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Mistral Large has 51.