Model comparison
Llama 2-7B vs Mistral
Llama 2-7B and Mistral score almost the same on the Noometry Index (28.6 vs 29.4), 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 2-7B scores higher in 2 categories and Mistral in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 2-7B leads 27.7 to 16.3.
- Llama 2-7B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-7B | Mistral | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 28.6 | 29.4 |
| Released | 2023-07-18 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 29 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Llama 2-7B: 28.7 (#302), Mistral: 33.2 (#249)
| Benchmark | Llama 2-7B | Mistral |
|---|---|---|
| LMArena Coding | 1002 | 1162 |
Reasoning Mistral leads
Llama 2-7B: 15.1 (#309), Mistral: 21.3 (#199)
| Benchmark | Llama 2-7B | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1009 | 1149 |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | 39.2% | — |
| Epoch Capabilities Index | 98.54 | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math Llama 2-7B leads
Llama 2-7B: 28.2 (#231), Mistral: 20.5 (#275)
| Benchmark | Llama 2-7B | Mistral |
|---|---|---|
| LMArena Math | 1042 | 1180 |
| Omni-MATH | — | 7.2% |
| GSM8K | 16.7% | — |
Knowledge Llama 2-7B leads
Llama 2-7B: 27.7 (#243), Mistral: 16.3 (#283)
| Benchmark | Llama 2-7B | Mistral |
|---|---|---|
| LMArena Expert | 1036 | 1125 |
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| ARC (AI2) Challenge | 45.9% | — |
| BoolQ | 77.9% | — |
| MMLU | 45.8% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |
Multimodal Not comparable
Llama 2-7B: —, Mistral: —
| Benchmark | Llama 2-7B | Mistral |
|---|---|---|
| ScienceQA | 43.1% | — |
Multilingual Mistral leads
Llama 2-7B: 23.9 (#288), Mistral: 33.0 (#249)
| Benchmark | Llama 2-7B | Mistral |
|---|---|---|
| LMArena Non-English | 973 | 1129 |
| LMArena Chinese | 973 | 1109 |
| LMArena French | 969 | 1179 |
| LMArena German | 978 | 1155 |
| LMArena Russian | 995 | 1168 |
| LMArena Spanish | 1007 | 1143 |
| LMArena Japanese | — | 1012 |
| LMArena Korean | — | 1032 |
Instruction Following Mistral leads
Llama 2-7B: 51.0 (#293), Mistral: 52.9 (#283)
| Benchmark | Llama 2-7B | Mistral |
|---|---|---|
| LMArena Instruction Following | 1006 | 1152 |
| IFEval | — | 56.8% |
Long Context Mistral leads
Llama 2-7B: 30.4 (#282), Mistral: 35.0 (#240)
| Benchmark | Llama 2-7B | Mistral |
|---|---|---|
| LMArena Longer Query | 999 | 1154 |
Writing & Preference Mistral leads
Llama 2-7B: 28.1 (#293), Mistral: 37.2 (#255)
| Benchmark | Llama 2-7B | Mistral |
|---|---|---|
| LMArena Text | 1053 | 1165 |
| LMArena Creative Writing | 1033 | 1158 |
| LMArena Multi-Turn | 1029 | 1147 |
| WildBench | — | 66% |
Frequently asked questions
Is Llama 2-7B better than Mistral?
Llama 2-7B and Mistral score almost the same on the Noometry Index (28.6 vs 29.4), so choose on price, context window or the category you care about most.
Is Llama 2-7B or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.2 versus 28.7 in the Noometry coding category.
How many benchmarks do Llama 2-7B and Mistral share?
15 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Mistral has 22.