Model comparison
Llama 2-7B vs Ministral 8B
Llama 2-7B and Ministral 8B score almost the same on the Noometry Index (29.1 vs 28.2), so choose on price, context window or the category you care about most.
Last verified . 12 shared benchmarks.
Meta
Mistral AISummary
- They share 12 benchmarks with published results for both. Llama 2-7B scores higher in 2 categories and Ministral 8B in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 2-7B leads 28.2 to 12.6.
Side by side
| Llama 2-7B | Ministral 8B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 29.1 | 28.2 |
| Released | 2023-07-18 | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 29 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ministral 8B leads
Llama 2-7B: 29.2 (#307), Ministral 8B: 35.0 (#230)
| Benchmark | Llama 2-7B | Ministral 8B |
|---|---|---|
| LMArena Coding | 1002 | 1202 |
Agentic & Tool Use Not comparable
Llama 2-7B: —, Ministral 8B: 16.4 (#148)
| Benchmark | Llama 2-7B | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
Reasoning Ministral 8B leads
Llama 2-7B: 15.7 (#312), Ministral 8B: 18.4 (#281)
| Benchmark | Llama 2-7B | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1009 | 1191 |
| Chess Puzzles | 0% | — |
| DTBench | — | 45.7% |
| BIG-Bench Hard | 39.2% | — |
| Epoch Capabilities Index | 99.06 | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math Llama 2-7B leads
Llama 2-7B: 30.7 (#233), Ministral 8B: 25.7 (#267)
| Benchmark | Llama 2-7B | Ministral 8B |
|---|---|---|
| LMArena Math | 1042 | 1188 |
| MATH Level 5 | — | 14.9% |
| GSM8K | 16.7% | — |
Knowledge Llama 2-7B leads
Llama 2-7B: 28.2 (#248), Ministral 8B: 12.6 (#297)
| Benchmark | Llama 2-7B | Ministral 8B |
|---|---|---|
| LMArena Expert | 1036 | 1170 |
| GPQA Diamond | — | 27.1% |
| Vectara Hallucination Rate | — | 7.4% |
| ARC (AI2) Challenge | 45.9% | — |
| BoolQ | 77.9% | — |
| MMLU | 45.8% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |
Multimodal Not comparable
Llama 2-7B: —, Ministral 8B: —
| Benchmark | Llama 2-7B | Ministral 8B |
|---|---|---|
| ScienceQA | 43.1% | — |
Multilingual Ministral 8B leads
Llama 2-7B: 23.8 (#293), Ministral 8B: 35.1 (#247)
| Benchmark | Llama 2-7B | Ministral 8B |
|---|---|---|
| LMArena Non-English | 973 | 1165 |
| LMArena Chinese | 973 | 1193 |
| LMArena Russian | 995 | 1195 |
| LMArena French | 970 | — |
| LMArena German | 978 | — |
| LMArena Spanish | 1007 | — |
Instruction Following Ministral 8B leads
Llama 2-7B: 50.8 (#298), Ministral 8B: 60.5 (#250)
| Benchmark | Llama 2-7B | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1006 | 1161 |
Long Context Ministral 8B leads
Llama 2-7B: 30.4 (#287), Ministral 8B: 36.7 (#227)
| Benchmark | Llama 2-7B | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 999 | 1212 |
Writing & Preference Ministral 8B leads
Llama 2-7B: 28.0 (#298), Ministral 8B: 39.6 (#246)
| Benchmark | Llama 2-7B | Ministral 8B |
|---|---|---|
| LMArena Text | 1053 | 1191 |
| LMArena Creative Writing | 1033 | 1175 |
| LMArena Multi-Turn | 1029 | 1166 |
Frequently asked questions
Is Llama 2-7B better than Ministral 8B?
Llama 2-7B and Ministral 8B score almost the same on the Noometry Index (29.1 vs 28.2), so choose on price, context window or the category you care about most.
Is Llama 2-7B or Ministral 8B better for coding?
Ministral 8B scores higher on coding benchmarks: 35.0 versus 29.2 in the Noometry coding category.
How many benchmarks do Llama 2-7B and Ministral 8B share?
12 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Ministral 8B has 17.