Model comparison
Llama 3.1-405B vs Ministral 8B
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 28.2 on the Noometry Index.
Last verified . 15 shared benchmarks.
Meta
Mistral AISummary
- They share 15 benchmarks with published results for both. Llama 3.1-405B scores higher in 5 categories and Ministral 8B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.1-405B leads 30.4 to 12.6.
- The biggest single-benchmark swing is MATH Level 5: 49.8% for Llama 3.1-405B and 14.9% for Ministral 8B.
Side by side
| Llama 3.1-405B | Ministral 8B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.7 | 28.2 |
| Released | 2024-07-23 | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 42 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Llama 3.1-405B: 33.1 (#262), Ministral 8B: 35.0 (#230)
| Benchmark | Llama 3.1-405B | Ministral 8B |
|---|---|---|
| LMArena Coding | 1291 | 1202 |
| WeirdML | 21.4% | — |
Agentic & Tool Use Llama 3.1-405B leads
Llama 3.1-405B: 21.0 (#140), Ministral 8B: 16.4 (#148)
| Benchmark | Llama 3.1-405B | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Ministral 8B leads
Llama 3.1-405B: 16.8 (#300), Ministral 8B: 18.4 (#281)
| Benchmark | Llama 3.1-405B | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1191 |
| DTBench | 61.4% | 45.7% |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.75 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Ministral 8B leads
Llama 3.1-405B: 18.4 (#290), Ministral 8B: 25.7 (#267)
| Benchmark | Llama 3.1-405B | Ministral 8B |
|---|---|---|
| LMArena Math | 1281 | 1188 |
| MATH Level 5 | 49.8% | 14.9% |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
Knowledge Llama 3.1-405B leads
Llama 3.1-405B: 30.4 (#227), Ministral 8B: 12.6 (#297)
| Benchmark | Llama 3.1-405B | Ministral 8B |
|---|---|---|
| GPQA Diamond | 50.9% | 27.1% |
| LMArena Expert | 1243 | 1170 |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| Vectara Hallucination Rate | — | 7.4% |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Llama 3.1-405B leads
Llama 3.1-405B: 40.7 (#214), Ministral 8B: 35.1 (#247)
| Benchmark | Llama 3.1-405B | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1248 | 1165 |
| LMArena Chinese | 1242 | 1193 |
| LMArena Russian | 1265 | 1195 |
| LMArena French | 1279 | — |
| LMArena German | 1252 | — |
| LMArena Japanese | 1208 | — |
| LMArena Korean | 1184 | — |
| LMArena Spanish | 1260 | — |
Instruction Following Llama 3.1-405B leads
Llama 3.1-405B: 65.9 (#214), Ministral 8B: 60.5 (#250)
| Benchmark | Llama 3.1-405B | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1259 | 1161 |
| IFEval | 81.1% | — |
Long Context Llama 3.1-405B leads
Llama 3.1-405B: 38.4 (#197), Ministral 8B: 36.7 (#227)
| Benchmark | Llama 3.1-405B | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1266 | 1212 |
Writing & Preference Too close to call
Llama 3.1-405B: 38.9 (#251), Ministral 8B: 39.6 (#246)
| Benchmark | Llama 3.1-405B | Ministral 8B |
|---|---|---|
| LMArena Text | 1284 | 1191 |
| LMArena Creative Writing | 1262 | 1175 |
| LMArena Multi-Turn | 1297 | 1166 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Ministral 8B?
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 28.2 on the Noometry Index.
Is Llama 3.1-405B or Ministral 8B better for coding?
Ministral 8B scores higher on coding benchmarks: 35.0 versus 33.1 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Ministral 8B share?
15 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Ministral 8B has 17.