Model comparison
Llama 13b vs Mistral
Mistral is the stronger model overall, scoring 29.9 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 Mistral in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral leads 37.0 to 13.8.
- Llama 13b has downloadable open weights; the other is API-only.
Side by side
| Llama 13b | Mistral | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 24.4 | 29.9 |
| Released | 2023-02-24 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Llama 13b: 21.4 (#337), Mistral: 33.8 (#250)
| Benchmark | Llama 13b | Mistral |
|---|---|---|
| LMArena Coding | 683 | 1162 |
Reasoning Mistral leads
Llama 13b: 14.0 (#329), Mistral: 22.2 (#200)
| Benchmark | Llama 13b | Mistral |
|---|---|---|
| LMArena Hard Prompts | 728 | 1149 |
| BIG-Bench Hard | 37.9% | — |
| Epoch Capabilities Index | 100.58 | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math Llama 13b leads
Llama 13b: 26.7 (#256), Mistral: 22.3 (#278)
| Benchmark | Llama 13b | Mistral |
|---|---|---|
| LMArena Math | 838 | 1180 |
| Omni-MATH | — | 7.2% |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Mistral: 16.6 (#288)
| Benchmark | Llama 13b | Mistral |
|---|---|---|
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| LMArena Expert | — | 1125 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Mistral: —
| Benchmark | Llama 13b | Mistral |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Mistral leads
Llama 13b: 16.6 (#297), Mistral: 32.8 (#254)
| Benchmark | Llama 13b | Mistral |
|---|---|---|
| LMArena Non-English | 819 | 1129 |
| LMArena Chinese | — | 1109 |
| LMArena French | — | 1180 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1013 |
| LMArena Korean | — | 1032 |
| LMArena Russian | — | 1168 |
| LMArena Spanish | — | 1143 |
Instruction Following Mistral leads
Llama 13b: 36.7 (#305), Mistral: 52.6 (#288)
| Benchmark | Llama 13b | Mistral |
|---|---|---|
| LMArena Instruction Following | 781 | 1152 |
| IFEval | — | 56.8% |
Long Context Not comparable
Llama 13b: —, Mistral: 35.0 (#245)
| Benchmark | Llama 13b | Mistral |
|---|---|---|
| LMArena Longer Query | — | 1153 |
Writing & Preference Mistral leads
Llama 13b: 13.8 (#312), Mistral: 37.0 (#260)
| Benchmark | Llama 13b | Mistral |
|---|---|---|
| LMArena Text | 834 | 1165 |
| LMArena Creative Writing | 794 | 1158 |
| LMArena Multi-Turn | 753 | 1147 |
| WildBench | — | 66% |
Frequently asked questions
Is Llama 13b better than Mistral?
Mistral is the stronger model overall, scoring 29.9 to 24.4 on the Noometry Index.
Is Llama 13b or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.8 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and Mistral share?
8 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Mistral has 22.