Model comparison
Llama 13b vs Ministral 8B
Ministral 8B is the stronger model overall, scoring 28.2 to 24.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
Meta
Mistral AISummary
- They share 8 benchmarks with published results for both. Llama 13b scores higher in 1 category and Ministral 8B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Ministral 8B leads 39.6 to 13.8.
Side by side
| Llama 13b | Ministral 8B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 24.4 | 28.2 |
| Released | 2023-02-24 | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 21 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Llama 13b: 21.4 (#337), Ministral 8B: 35.0 (#230)
| Benchmark | Llama 13b | Ministral 8B |
|---|---|---|
| LMArena Coding | 683 | 1202 |
Agentic & Tool Use Not comparable
Llama 13b: —, Ministral 8B: 16.4 (#148)
| Benchmark | Llama 13b | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Ministral 8B leads
Llama 13b: 14.0 (#329), Ministral 8B: 18.4 (#281)
| Benchmark | Llama 13b | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 728 | 1191 |
| DTBench | — | 45.7% |
| BIG-Bench Hard | 37.9% | — |
| Epoch Capabilities Index | 100.58 | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math Too close to call
Llama 13b: 26.7 (#256), Ministral 8B: 25.7 (#267)
| Benchmark | Llama 13b | Ministral 8B |
|---|---|---|
| LMArena Math | 838 | 1188 |
| MATH Level 5 | — | 14.9% |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Ministral 8B: 12.6 (#297)
| Benchmark | Llama 13b | Ministral 8B |
|---|---|---|
| GPQA Diamond | — | 27.1% |
| Vectara Hallucination Rate | — | 7.4% |
| LMArena Expert | — | 1170 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Ministral 8B: —
| Benchmark | Llama 13b | Ministral 8B |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Ministral 8B leads
Llama 13b: 16.6 (#297), Ministral 8B: 35.1 (#247)
| Benchmark | Llama 13b | Ministral 8B |
|---|---|---|
| LMArena Non-English | 819 | 1165 |
| LMArena Chinese | — | 1193 |
| LMArena Russian | — | 1195 |
Instruction Following Ministral 8B leads
Llama 13b: 36.7 (#305), Ministral 8B: 60.5 (#250)
| Benchmark | Llama 13b | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 781 | 1161 |
Long Context Not comparable
Llama 13b: —, Ministral 8B: 36.7 (#227)
| Benchmark | Llama 13b | Ministral 8B |
|---|---|---|
| LMArena Longer Query | — | 1212 |
Writing & Preference Ministral 8B leads
Llama 13b: 13.8 (#312), Ministral 8B: 39.6 (#246)
| Benchmark | Llama 13b | Ministral 8B |
|---|---|---|
| LMArena Text | 834 | 1191 |
| LMArena Creative Writing | 794 | 1175 |
| LMArena Multi-Turn | 753 | 1166 |
Frequently asked questions
Is Llama 13b better than Ministral 8B?
Ministral 8B is the stronger model overall, scoring 28.2 to 24.4 on the Noometry Index.
Is Llama 13b or Ministral 8B better for coding?
Ministral 8B scores higher on coding benchmarks: 35.0 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and Ministral 8B share?
8 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Ministral 8B has 17.