Model comparison
Llama 3.1-405B vs Mistral
Llama 3.1-405B and Mistral score almost the same on the Noometry Index (30.7 vs 29.9), so choose on price, context window or the category you care about most.
Last verified . 22 shared benchmarks.
Meta
Mistral AISummary
- They share 22 benchmarks with published results for both. Llama 3.1-405B scores higher in 5 categories and Mistral in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.1-405B leads 30.4 to 16.6.
- The biggest single-benchmark swing is MMLU-Pro: 72.3% for Llama 3.1-405B and 27.7% for Mistral.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-405B | Mistral | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.7 | 29.9 |
| Released | 2024-07-23 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 22 |
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: 33.8 (#250)
| Benchmark | Llama 3.1-405B | Mistral |
|---|---|---|
| LMArena Coding | 1291 | 1162 |
| WeirdML | 21.4% | — |
Agentic & Tool Use Not comparable
Llama 3.1-405B: 21.0 (#140), Mistral: —
| Benchmark | Llama 3.1-405B | Mistral |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Mistral leads
Llama 3.1-405B: 16.8 (#300), Mistral: 22.2 (#200)
| Benchmark | Llama 3.1-405B | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1149 |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| DTBench | 61.4% | — |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.75 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Mistral leads
Llama 3.1-405B: 18.4 (#290), Mistral: 22.3 (#278)
| Benchmark | Llama 3.1-405B | Mistral |
|---|---|---|
| Omni-MATH | 24.9% | 7.2% |
| LMArena Math | 1281 | 1180 |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| MATH Level 5 | 49.8% | — |
Knowledge Llama 3.1-405B leads
Llama 3.1-405B: 30.4 (#227), Mistral: 16.6 (#288)
| Benchmark | Llama 3.1-405B | Mistral |
|---|---|---|
| MMLU-Pro | 72.3% | 27.7% |
| GPQA (HELM) | 52.2% | 30.3% |
| LMArena Expert | 1243 | 1125 |
| GPQA Diamond | 50.9% | — |
| Confabulations | 17.6% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Llama 3.1-405B leads
Llama 3.1-405B: 40.7 (#214), Mistral: 32.8 (#254)
| Benchmark | Llama 3.1-405B | Mistral |
|---|---|---|
| LMArena Non-English | 1248 | 1129 |
| LMArena Chinese | 1242 | 1109 |
| LMArena French | 1279 | 1180 |
| LMArena German | 1252 | 1155 |
| LMArena Japanese | 1208 | 1013 |
| LMArena Korean | 1184 | 1032 |
| LMArena Russian | 1265 | 1168 |
| LMArena Spanish | 1260 | 1143 |
Instruction Following Llama 3.1-405B leads
Llama 3.1-405B: 65.9 (#214), Mistral: 52.6 (#288)
| Benchmark | Llama 3.1-405B | Mistral |
|---|---|---|
| IFEval | 81.1% | 56.8% |
| LMArena Instruction Following | 1259 | 1152 |
Long Context Llama 3.1-405B leads
Llama 3.1-405B: 38.4 (#197), Mistral: 35.0 (#245)
| Benchmark | Llama 3.1-405B | Mistral |
|---|---|---|
| LMArena Longer Query | 1266 | 1153 |
Writing & Preference Llama 3.1-405B leads
Llama 3.1-405B: 38.9 (#251), Mistral: 37.0 (#260)
| Benchmark | Llama 3.1-405B | Mistral |
|---|---|---|
| LMArena Text | 1284 | 1165 |
| LMArena Creative Writing | 1262 | 1158 |
| WildBench | 78.3% | 66% |
| LMArena Multi-Turn | 1297 | 1147 |
| EQ-Bench Creative Writing | 870 | — |
Frequently asked questions
Is Llama 3.1-405B better than Mistral?
Llama 3.1-405B and Mistral score almost the same on the Noometry Index (30.7 vs 29.9), so choose on price, context window or the category you care about most.
Is Llama 3.1-405B or Mistral better for coding?
They score almost the same on coding (33.1 vs 33.8); test both on your own repository before choosing.
How many benchmarks do Llama 3.1-405B and Mistral share?
22 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Mistral has 22.