Model comparison
Llama 3-70B vs Ministral 3B
Llama 3-70B is the stronger model overall, scoring 28.5 to 25.6 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
Mistral AISummary
- They share 4 benchmarks with published results for both. Llama 3-70B scores higher in 1 category and Ministral 3B in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Ministral 3B leads 24.5 to 12.0.
- The biggest single-benchmark swing is GPQA Diamond: 40.6% for Llama 3-70B and 25.3% for Ministral 3B.
Side by side
| Llama 3-70B | Ministral 3B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 28.5 | 25.6 |
| Released | 2024-04-18 | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.04 |
| Output $ / M tokens | — | $0.04 |
| Results tracked | 31 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3-70B: 35.3 (#215), Ministral 3B: —
| Benchmark | Llama 3-70B | Ministral 3B |
|---|---|---|
| BigCodeBench Instruct | 43.6% | — |
| LMArena Coding | 1206 | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 20.9 (#132), Ministral 3B: —
| Benchmark | Llama 3-70B | Ministral 3B |
|---|---|---|
| Cybench | 5% | — |
Reasoning Too close to call
Llama 3-70B: 17.4 (#284), Ministral 3B: 17.7 (#278)
| Benchmark | Llama 3-70B | Ministral 3B |
|---|---|---|
| DTBench | 54.2% | 51.7% |
| Epoch Capabilities Index | 122.91 | 118.08 |
| Kagi LLM Benchmark | 35.1% | — |
| LMArena Hard Prompts | 1195 | — |
| LMCA | — | 5.5% |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Ministral 3B leads
Llama 3-70B: 12.0 (#299), Ministral 3B: 24.5 (#257)
| Benchmark | Llama 3-70B | Ministral 3B |
|---|---|---|
| MATH Level 5 | 22.6% | 14.4% |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| LMArena Math | 1218 | — |
Knowledge Llama 3-70B leads
Llama 3-70B: 20.8 (#272), Ministral 3B: 10.4 (#297)
| Benchmark | Llama 3-70B | Ministral 3B |
|---|---|---|
| GPQA Diamond | 40.6% | 25.3% |
| Vectara Hallucination Rate | — | 7.3% |
| LMArena Expert | 1149 | — |
| MMLU | 79.3% | — |
Multilingual Not comparable
Llama 3-70B: 33.8 (#246), Ministral 3B: —
| Benchmark | Llama 3-70B | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1142 | — |
| LMArena Chinese | 1114 | — |
| LMArena French | 1231 | — |
| LMArena German | 1169 | — |
| LMArena Japanese | 1017 | — |
| LMArena Korean | 1017 | — |
| LMArena Russian | 1159 | — |
| LMArena Spanish | 1241 | — |
Instruction Following Not comparable
Llama 3-70B: 62.8 (#233), Ministral 3B: —
| Benchmark | Llama 3-70B | Ministral 3B |
|---|---|---|
| LMArena Instruction Following | 1194 | — |
Long Context Not comparable
Llama 3-70B: 35.6 (#235), Ministral 3B: —
| Benchmark | Llama 3-70B | Ministral 3B |
|---|---|---|
| LMArena Longer Query | 1174 | — |
Writing & Preference Not comparable
Llama 3-70B: 43.0 (#225), Ministral 3B: —
| Benchmark | Llama 3-70B | Ministral 3B |
|---|---|---|
| LMArena Text | 1221 | — |
| LMArena Creative Writing | 1210 | — |
| LMArena Multi-Turn | 1223 | — |
Frequently asked questions
Is Llama 3-70B better than Ministral 3B?
Llama 3-70B is the stronger model overall, scoring 28.5 to 25.6 on the Noometry Index.
How many benchmarks do Llama 3-70B and Ministral 3B share?
4 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Ministral 3B has 6.