Model comparison
Llama 3.1-405B vs Mistral Small
Mistral Small is the stronger model overall, scoring 33.4 to 30.7 on the Noometry Index.
Last verified . 23 shared benchmarks.
Meta
Mistral AISummary
- They share 23 benchmarks with published results for both. Llama 3.1-405B scores higher in 1 category and Mistral Small in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Small leads 52.5 to 38.9.
- The biggest single-benchmark swing is DTBench: 61.4% for Llama 3.1-405B and 70.9% for Mistral Small.
Side by side
| Llama 3.1-405B | Mistral Small | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.7 | 33.4 |
| Released | 2024-07-23 | 2024-02-26 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.60 |
| Results tracked | 42 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3.1-405B: 33.1 (#262), Mistral Small: 34.0 (#247)
| Benchmark | Llama 3.1-405B | Mistral Small |
|---|---|---|
| LMArena Coding | 1291 | 1362 |
| SciCode | — | 26.5% |
| WeirdML | 21.4% | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |
Agentic & Tool Use Mistral Small leads
Llama 3.1-405B: 21.0 (#140), Mistral Small: 28.1 (#93)
| Benchmark | Llama 3.1-405B | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Mistral Small leads
Llama 3.1-405B: 16.8 (#300), Mistral Small: 19.8 (#250)
| Benchmark | Llama 3.1-405B | Mistral Small |
|---|---|---|
| Kagi LLM Benchmark | 45% | 37.8% |
| LMArena Hard Prompts | 1269 | 1335 |
| DTBench | 61.4% | 70.9% |
| SimpleBench | 23% | — |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.75 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| LiveBench | — | 44% |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Llama 3.1-405B leads
Llama 3.1-405B: 18.4 (#290), Mistral Small: 16.4 (#293)
| Benchmark | Llama 3.1-405B | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 9.7% | 5.8% |
| LMArena Math | 1281 | 1341 |
| MATH Level 5 | 49.8% | 46.8% |
| Omni-MATH | 24.9% | — |
| LiveBench Math | — | 39.9% |
Knowledge Too close to call
Llama 3.1-405B: 30.4 (#227), Mistral Small: 31.0 (#222)
| Benchmark | Llama 3.1-405B | Mistral Small |
|---|---|---|
| GPQA Diamond | 50.9% | 47.5% |
| LMArena Expert | 1243 | 1291 |
| MMLU | 84.5% | 68.7% |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| Vectara Hallucination Rate | — | 5.1% |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| TriviaQA | 82.7% | — |
Multimodal Not comparable
Llama 3.1-405B: —, Mistral Small: 33.5 (#96)
| Benchmark | Llama 3.1-405B | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |
Multilingual Mistral Small leads
Llama 3.1-405B: 40.7 (#214), Mistral Small: 45.5 (#169)
| Benchmark | Llama 3.1-405B | Mistral Small |
|---|---|---|
| LMArena Non-English | 1248 | 1315 |
| LMArena Chinese | 1242 | 1340 |
| LMArena French | 1279 | 1337 |
| LMArena German | 1252 | 1340 |
| LMArena Japanese | 1208 | 1275 |
| LMArena Korean | 1184 | 1259 |
| LMArena Russian | 1265 | 1324 |
| LMArena Spanish | 1260 | 1346 |
Instruction Following Too close to call
Llama 3.1-405B: 65.9 (#214), Mistral Small: 66.4 (#209)
| Benchmark | Llama 3.1-405B | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1259 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
| IFEval | 81.1% | — |
Long Context Mistral Small leads
Llama 3.1-405B: 38.4 (#197), Mistral Small: 40.4 (#156)
| Benchmark | Llama 3.1-405B | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1266 | 1327 |
Writing & Preference Mistral Small leads
Llama 3.1-405B: 38.9 (#251), Mistral Small: 52.5 (#171)
| Benchmark | Llama 3.1-405B | Mistral Small |
|---|---|---|
| LMArena Text | 1284 | 1338 |
| LMArena Creative Writing | 1262 | 1305 |
| LMArena Multi-Turn | 1297 | 1344 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is Llama 3.1-405B better than Mistral Small?
Mistral Small is the stronger model overall, scoring 33.4 to 30.7 on the Noometry Index.
Is Llama 3.1-405B or Mistral Small better for coding?
They score almost the same on coding (33.1 vs 34.0); test both on your own repository before choosing.
How many benchmarks do Llama 3.1-405B and Mistral Small share?
23 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Mistral Small has 39.