Model comparison
Llama 3-8B vs Ministral 3B
Llama 3-8B and Ministral 3B score almost the same on the Noometry Index (25.5 vs 26.2), so choose on price, context window or the category you care about most.
Last verified . 4 shared benchmarks.
Meta
Mistral AISummary
- They share 4 benchmarks with published results for both. Llama 3-8B scores higher in 0 categories and Ministral 3B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Ministral 3B leads 26.6 to 8.8.
- The biggest single-benchmark swing is MATH Level 5: 6.1% for Llama 3-8B and 14.4% for Ministral 3B.
Side by side
| Llama 3-8B | Ministral 3B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 25.5 | 26.2 |
| Released | 2024-04-18 | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.10 |
| Results tracked | 34 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3-8B: 31.0 (#289), Ministral 3B: —
| Benchmark | Llama 3-8B | Ministral 3B |
|---|---|---|
| BigCodeBench Instruct | 31.9% | — |
| LMArena Coding | 1152 | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Ministral 3B leads
Llama 3-8B: 14.3 (#326), Ministral 3B: 18.4 (#282)
| Benchmark | Llama 3-8B | Ministral 3B |
|---|---|---|
| DTBench | 43.9% | 51.7% |
| Epoch Capabilities Index | 116.45 | 118.1 |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1133 | — |
| LMCA | — | 5.5% |
| Adversarial NLI | 57.3% | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Ministral 3B leads
Llama 3-8B: 8.8 (#323), Ministral 3B: 26.6 (#258)
| Benchmark | Llama 3-8B | Ministral 3B |
|---|---|---|
| MATH Level 5 | 6.1% | 14.4% |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| LMArena Math | 1151 | — |
Knowledge Ministral 3B leads
Llama 3-8B: 7.8 (#308), Ministral 3B: 10.4 (#302)
| Benchmark | Llama 3-8B | Ministral 3B |
|---|---|---|
| GPQA Diamond | 26.1% | 25.3% |
| Vectara Hallucination Rate | — | 7.3% |
| LMArena Expert | 1113 | — |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Not comparable
Llama 3-8B: 30.8 (#261), Ministral 3B: —
| Benchmark | Llama 3-8B | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1098 | — |
| LMArena Chinese | 1076 | — |
| LMArena French | 1159 | — |
| LMArena German | 1104 | — |
| LMArena Japanese | 967 | — |
| LMArena Korean | 1004 | — |
| LMArena Russian | 1109 | — |
| LMArena Spanish | 1173 | — |
Instruction Following Not comparable
Llama 3-8B: 58.4 (#260), Ministral 3B: —
| Benchmark | Llama 3-8B | Ministral 3B |
|---|---|---|
| LMArena Instruction Following | 1127 | — |
Long Context Not comparable
Llama 3-8B: 34.2 (#251), Ministral 3B: —
| Benchmark | Llama 3-8B | Ministral 3B |
|---|---|---|
| LMArena Longer Query | 1128 | — |
Writing & Preference Not comparable
Llama 3-8B: 37.5 (#256), Ministral 3B: —
| Benchmark | Llama 3-8B | Ministral 3B |
|---|---|---|
| LMArena Text | 1166 | — |
| LMArena Creative Writing | 1150 | — |
| LMArena Multi-Turn | 1152 | — |
Frequently asked questions
Is Llama 3-8B better than Ministral 3B?
Llama 3-8B and Ministral 3B score almost the same on the Noometry Index (25.5 vs 26.2), so choose on price, context window or the category you care about most.
How many benchmarks do Llama 3-8B and Ministral 3B share?
4 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Ministral 3B has 6.