Model comparison
Claude 3 Opus vs Mistral Small 3.1
Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 29.5 on the Noometry Index.
Last verified . 22 shared benchmarks.
Mistral AISummary
- They share 22 benchmarks with published results for both. Claude 3 Opus scores higher in 5 categories and Mistral Small 3.1 in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Claude 3 Opus leads 47.2 to 37.0.
- The biggest single-benchmark swing is GPQA Diamond: 47.2% for Claude 3 Opus and 41.9% for Mistral Small 3.1.
- Mistral Small 3.1 has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Opus | Mistral Small 3.1 | |
|---|---|---|
| Provider | Anthropic | Mistral AI |
| Noometry Index | 29.5 | 31.7 |
| Released | 2024-02-29 | 2025-03-17 |
| Weights | Proprietary | Open |
| Context window | — | 128K |
| Max output | — | 102K |
| Input $ / M tokens | — | $0.35 |
| Output $ / M tokens | — | $0.56 |
| Results tracked | 46 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3.1 leads
Claude 3 Opus: 32.9 (#267), Mistral Small 3.1: 38.3 (#179)
| Benchmark | Claude 3 Opus | Mistral Small 3.1 |
|---|---|---|
| LMArena Coding | 1264 | 1309 |
| WeirdML | 19.2% | — |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
Claude 3 Opus: 24.6 (#116), Mistral Small 3.1: —
| Benchmark | Claude 3 Opus | Mistral Small 3.1 |
|---|---|---|
| Cybench | 10% | — |
| METR Time Horizons | 29.5% | — |
Reasoning Mistral Small 3.1 leads
Claude 3 Opus: 14.6 (#324), Mistral Small 3.1: 19.7 (#254)
| Benchmark | Claude 3 Opus | Mistral Small 3.1 |
|---|---|---|
| Chess Puzzles | 5% | 1% |
| LMArena Hard Prompts | 1245 | 1278 |
| Epoch Capabilities Index | 126.91 | 127.48 |
| SimpleBench | 23.5% | — |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| DTBench | 61.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| LMCA | 17% | — |
| ForecastBench | 58.4 | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Too close to call
Claude 3 Opus: 14.8 (#299), Mistral Small 3.1: 14.7 (#301)
| Benchmark | Claude 3 Opus | Mistral Small 3.1 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.7% | 3.9% |
| LMArena Math | 1273 | 1262 |
| Omni-MATH | — | 24.8% |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
Knowledge Claude 3 Opus leads
Claude 3 Opus: 24.5 (#267), Mistral Small 3.1: 22.6 (#271)
| Benchmark | Claude 3 Opus | Mistral Small 3.1 |
|---|---|---|
| GPQA Diamond | 47.2% | 41.9% |
| LMArena Expert | 1223 | 1257 |
| SimpleQA Verified | 12.6% | — |
| MMLU-Pro | — | 61% |
| Confabulations | 22.7% | — |
| GPQA (HELM) | — | 39.2% |
| MMLU | 84.6% | — |
Multimodal Mistral Small 3.1 leads
Claude 3 Opus: 27.1 (#116), Mistral Small 3.1: 33.2 (#99)
| Benchmark | Claude 3 Opus | Mistral Small 3.1 |
|---|---|---|
| LMArena Vision | 1023 | 1136 |
Multilingual Too close to call
Claude 3 Opus: 41.4 (#207), Mistral Small 3.1: 41.2 (#209)
| Benchmark | Claude 3 Opus | Mistral Small 3.1 |
|---|---|---|
| LMArena Non-English | 1258 | 1255 |
| LMArena Chinese | 1248 | 1253 |
| LMArena French | 1275 | 1273 |
| LMArena German | 1258 | 1266 |
| LMArena Japanese | 1204 | 1208 |
| LMArena Korean | 1187 | 1206 |
| LMArena Russian | 1280 | 1263 |
| LMArena Spanish | 1246 | 1283 |
Instruction Following Too close to call
Claude 3 Opus: 64.1 (#228), Mistral Small 3.1: 63.6 (#230)
| Benchmark | Claude 3 Opus | Mistral Small 3.1 |
|---|---|---|
| LMArena Instruction Following | 1248 | 1264 |
| LiveBench Instruction Following | 63.9% | — |
| IFEval | — | 75% |
Long Context Mistral Small 3.1 leads
Claude 3 Opus: 38.2 (#202), Mistral Small 3.1: 39.5 (#178)
| Benchmark | Claude 3 Opus | Mistral Small 3.1 |
|---|---|---|
| LMArena Longer Query | 1259 | 1299 |
Writing & Preference Claude 3 Opus leads
Claude 3 Opus: 47.2 (#213), Mistral Small 3.1: 37.0 (#259)
| Benchmark | Claude 3 Opus | Mistral Small 3.1 |
|---|---|---|
| LMArena Text | 1262 | 1277 |
| LMArena Creative Writing | 1235 | 1253 |
| LMArena Multi-Turn | 1275 | 1270 |
| EQ-Bench Creative Writing | — | 761 |
| WildBench | — | 78.8% |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Mistral Small 3.1?
Mistral Small 3.1 is the stronger model overall, scoring 31.7 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Mistral Small 3.1 better for coding?
Mistral Small 3.1 scores higher on coding benchmarks: 38.3 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Mistral Small 3.1 share?
22 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Mistral Small 3.1 has 28.