Model comparison
Claude 3 Opus vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.4 to 29.5 on the Noometry Index.
Last verified . 33 shared benchmarks.
Mistral AISummary
- They share 33 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Mistral Small in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mistral Small leads 31.0 to 24.5.
- The biggest single-benchmark swing is LiveBench Language: 50.4% for Claude 3 Opus and 30.5% for Mistral Small.
- Mistral Small has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Opus | Mistral Small | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 29.5 | 33.4 |
| Released | 2024-02-29 | 2024-02-26 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 46 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small leads
Claude 3 Opus: 32.9 (#267), Mistral Small: 34.0 (#247)
| Benchmark | Claude 3 Opus | Mistral Small |
|---|---|---|
| BigCodeBench Instruct | 45.5% | 36.1% |
| LiveBench Coding | 38.6% | 36.2% |
| LMArena Coding | 1264 | 1362 |
| BigCodeBench Complete | 57.4% | 46.6% |
| SciCode | — | 26.5% |
| WeirdML | 19.2% | — |
| ALE-Bench | — | 497.62 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Mistral Small leads
Claude 3 Opus: 24.6 (#116), Mistral Small: 28.1 (#93)
| Benchmark | Claude 3 Opus | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
| Cybench | 10% | — |
| METR Time Horizons | 29.5% | — |
Reasoning Mistral Small leads
Claude 3 Opus: 14.6 (#324), Mistral Small: 19.8 (#250)
| Benchmark | Claude 3 Opus | Mistral Small |
|---|---|---|
| LiveBench Reasoning | 40.6% | 44.8% |
| LMArena Hard Prompts | 1245 | 1335 |
| DTBench | 61.6% | 70.9% |
| LiveBench Data Analysis | 57.9% | 53.7% |
| LMCA | 17% | 20.6% |
| LiveBench | 49.2% | 44% |
| SimpleBench | 23.5% | — |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| Chess Puzzles | 5% | — |
| EnigmaEval | 0.8% | — |
| Epoch Capabilities Index | 126.91 | — |
| ForecastBench | 58.4 | — |
| WinoGrande | 88.5% | — |
Math Mistral Small leads
Claude 3 Opus: 14.8 (#299), Mistral Small: 16.4 (#293)
| Benchmark | Claude 3 Opus | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 5.8% |
| LiveBench Math | 43.6% | 39.9% |
| LMArena Math | 1273 | 1341 |
| MATH Level 5 | 37.5% | 46.8% |
Knowledge Mistral Small leads
Claude 3 Opus: 24.5 (#267), Mistral Small: 31.0 (#222)
| Benchmark | Claude 3 Opus | Mistral Small |
|---|---|---|
| GPQA Diamond | 47.2% | 47.5% |
| LMArena Expert | 1223 | 1291 |
| MMLU | 84.6% | 68.7% |
| SimpleQA Verified | 12.6% | — |
| Confabulations | 22.7% | — |
| Vectara Hallucination Rate | — | 5.1% |
Multimodal Mistral Small leads
Claude 3 Opus: 27.1 (#116), Mistral Small: 33.5 (#96)
| Benchmark | Claude 3 Opus | Mistral Small |
|---|---|---|
| LMArena Vision | 1023 | 1142 |
Multilingual Mistral Small leads
Claude 3 Opus: 41.4 (#207), Mistral Small: 45.5 (#169)
| Benchmark | Claude 3 Opus | Mistral Small |
|---|---|---|
| LMArena Non-English | 1258 | 1315 |
| LMArena Chinese | 1248 | 1340 |
| LMArena French | 1275 | 1337 |
| LMArena German | 1258 | 1340 |
| LMArena Japanese | 1204 | 1275 |
| LMArena Korean | 1187 | 1259 |
| LMArena Russian | 1280 | 1324 |
| LMArena Spanish | 1246 | 1346 |
Instruction Following Mistral Small leads
Claude 3 Opus: 64.1 (#228), Mistral Small: 66.4 (#209)
| Benchmark | Claude 3 Opus | Mistral Small |
|---|---|---|
| LiveBench Instruction Following | 63.9% | 63.7% |
| LMArena Instruction Following | 1248 | 1310 |
Long Context Mistral Small leads
Claude 3 Opus: 38.2 (#202), Mistral Small: 40.4 (#156)
| Benchmark | Claude 3 Opus | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1259 | 1327 |
Writing & Preference Mistral Small leads
Claude 3 Opus: 47.2 (#213), Mistral Small: 52.5 (#171)
| Benchmark | Claude 3 Opus | Mistral Small |
|---|---|---|
| LMArena Text | 1262 | 1338 |
| LMArena Creative Writing | 1235 | 1305 |
| LMArena Multi-Turn | 1275 | 1344 |
| LiveBench Language | 50.4% | 30.5% |
Frequently asked questions
Is Claude 3 Opus better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.4 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Mistral Small better for coding?
Mistral Small scores higher on coding benchmarks: 34.0 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Mistral Small share?
33 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Mistral Small has 39.