Model comparison
Llama 3-70B vs Ministral 8B
Llama 3-70B and Ministral 8B score almost the same on the Noometry Index (28.8 vs 28.2), so choose on price, context window or the category you care about most.
Last verified . 15 shared benchmarks.
Meta
Mistral AISummary
- They share 15 benchmarks with published results for both. Llama 3-70B scores higher in 5 categories and Ministral 8B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Ministral 8B leads 25.7 to 12.8.
- The biggest single-benchmark swing is GPQA Diamond: 40.6% for Llama 3-70B and 27.1% for Ministral 8B.
Side by side
| Llama 3-70B | Ministral 8B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 28.8 | 28.2 |
| Released | 2024-04-18 | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 31 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3-70B: 35.8 (#218), Ministral 8B: 35.0 (#230)
| Benchmark | Llama 3-70B | Ministral 8B |
|---|---|---|
| LMArena Coding | 1206 | 1202 |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Llama 3-70B leads
Llama 3-70B: 21.1 (#139), Ministral 8B: 16.4 (#148)
| Benchmark | Llama 3-70B | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
| Cybench | 5% | — |
Reasoning Too close to call
Llama 3-70B: 18.0 (#288), Ministral 8B: 18.4 (#281)
| Benchmark | Llama 3-70B | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1191 |
| DTBench | 54.2% | 45.7% |
| Kagi LLM Benchmark | 35.1% | — |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Ministral 8B leads
Llama 3-70B: 12.8 (#305), Ministral 8B: 25.7 (#267)
| Benchmark | Llama 3-70B | Ministral 8B |
|---|---|---|
| LMArena Math | 1218 | 1188 |
| MATH Level 5 | 22.6% | 14.9% |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
Knowledge Llama 3-70B leads
Llama 3-70B: 20.8 (#277), Ministral 8B: 12.6 (#297)
| Benchmark | Llama 3-70B | Ministral 8B |
|---|---|---|
| GPQA Diamond | 40.6% | 27.1% |
| LMArena Expert | 1149 | 1170 |
| Vectara Hallucination Rate | — | 7.4% |
| MMLU | 79.3% | — |
Multilingual Ministral 8B leads
Llama 3-70B: 33.6 (#251), Ministral 8B: 35.1 (#247)
| Benchmark | Llama 3-70B | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1142 | 1165 |
| LMArena Chinese | 1114 | 1193 |
| LMArena Russian | 1159 | 1195 |
| LMArena French | 1232 | — |
| LMArena German | 1169 | — |
| LMArena Japanese | 1017 | — |
| LMArena Korean | 1017 | — |
| LMArena Spanish | 1241 | — |
Instruction Following Llama 3-70B leads
Llama 3-70B: 62.5 (#238), Ministral 8B: 60.5 (#250)
| Benchmark | Llama 3-70B | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1194 | 1161 |
Long Context Ministral 8B leads
Llama 3-70B: 35.6 (#240), Ministral 8B: 36.7 (#227)
| Benchmark | Llama 3-70B | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1174 | 1212 |
Writing & Preference Llama 3-70B leads
Llama 3-70B: 42.8 (#231), Ministral 8B: 39.6 (#246)
| Benchmark | Llama 3-70B | Ministral 8B |
|---|---|---|
| LMArena Text | 1221 | 1191 |
| LMArena Creative Writing | 1210 | 1175 |
| LMArena Multi-Turn | 1223 | 1166 |
Frequently asked questions
Is Llama 3-70B better than Ministral 8B?
Llama 3-70B and Ministral 8B score almost the same on the Noometry Index (28.8 vs 28.2), so choose on price, context window or the category you care about most.
Is Llama 3-70B or Ministral 8B better for coding?
They score almost the same on coding (35.8 vs 35.0); test both on your own repository before choosing.
How many benchmarks do Llama 3-70B and Ministral 8B share?
15 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Ministral 8B has 17.