Model comparison
Llama 2-70B vs Mistral
Mistral is the stronger model overall, scoring 29.4 to 24.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
Mistral AISummary
- They share 17 benchmarks with published results for both. Llama 2-70B scores higher in 1 category and Mistral in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Mistral leads 20.5 to 7.5.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-70B | Mistral | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 24.1 | 29.4 |
| Released | 2023-07-18 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Llama 2-70B: 30.8 (#281), Mistral: 33.2 (#249)
| Benchmark | Llama 2-70B | Mistral |
|---|---|---|
| LMArena Coding | 1079 | 1162 |
Reasoning Mistral leads
Llama 2-70B: 13.7 (#324), Mistral: 21.3 (#199)
| Benchmark | Llama 2-70B | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1149 |
| DTBench | 41.6% | — |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| Epoch Capabilities Index | 113.59 | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |
Math Mistral leads
Llama 2-70B: 7.5 (#320), Mistral: 20.5 (#275)
| Benchmark | Llama 2-70B | Mistral |
|---|---|---|
| LMArena Math | 1091 | 1180 |
| OTIS Mock AIME 2024-2025 | 0% | — |
| Omni-MATH | — | 7.2% |
| MATH Level 5 | 3.3% | — |
| GSM8K | 69.6% | — |
Knowledge Mistral leads
Llama 2-70B: 7.4 (#305), Mistral: 16.3 (#283)
| Benchmark | Llama 2-70B | Mistral |
|---|---|---|
| LMArena Expert | 1039 | 1125 |
| GPQA Diamond | 26.3% | — |
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual Mistral leads
Llama 2-70B: 27.9 (#269), Mistral: 33.0 (#249)
| Benchmark | Llama 2-70B | Mistral |
|---|---|---|
| LMArena Non-English | 1045 | 1129 |
| LMArena Chinese | 994 | 1109 |
| LMArena French | 1089 | 1179 |
| LMArena German | 1041 | 1155 |
| LMArena Japanese | 927 | 1012 |
| LMArena Korean | 964 | 1032 |
| LMArena Russian | 1083 | 1168 |
| LMArena Spanish | 1142 | 1143 |
Instruction Following Llama 2-70B leads
Llama 2-70B: 55.1 (#273), Mistral: 52.9 (#283)
| Benchmark | Llama 2-70B | Mistral |
|---|---|---|
| LMArena Instruction Following | 1071 | 1152 |
| IFEval | — | 56.8% |
Long Context Mistral leads
Llama 2-70B: 32.2 (#265), Mistral: 35.0 (#240)
| Benchmark | Llama 2-70B | Mistral |
|---|---|---|
| LMArena Longer Query | 1062 | 1154 |
Writing & Preference Mistral leads
Llama 2-70B: 32.5 (#274), Mistral: 37.2 (#255)
| Benchmark | Llama 2-70B | Mistral |
|---|---|---|
| LMArena Text | 1115 | 1165 |
| LMArena Creative Writing | 1075 | 1158 |
| LMArena Multi-Turn | 1088 | 1147 |
| WildBench | — | 66% |
Frequently asked questions
Is Llama 2-70B better than Mistral?
Mistral is the stronger model overall, scoring 29.4 to 24.1 on the Noometry Index.
Is Llama 2-70B or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.2 versus 30.8 in the Noometry coding category.
How many benchmarks do Llama 2-70B and Mistral share?
17 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Mistral has 22.