Model comparison
Llama 13b vs Mistral 7B
Llama 13b is the stronger model overall, scoring 24.4 to 23.0 on the Noometry Index.
Last verified . 19 shared benchmarks.
Meta
Mistral AISummary
- They share 19 benchmarks with published results for both. Llama 13b scores higher in 2 categories and Mistral 7B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 13b leads 26.7 to 8.1.
Side by side
| Llama 13b | Mistral 7B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 24.4 | 23.0 |
| Released | 2023-02-24 | 2023-09-27 |
| Weights | Open | Open |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.25 |
| Results tracked | 21 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral 7B leads
Llama 13b: 21.4 (#337), Mistral 7B: 26.4 (#326)
| Benchmark | Llama 13b | Mistral 7B |
|---|---|---|
| LMArena Coding | 683 | 1082 |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Reasoning Too close to call
Llama 13b: 14.0 (#329), Mistral 7B: 13.1 (#336)
| Benchmark | Llama 13b | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 728 | 1067 |
| BIG-Bench Hard | 37.9% | 56.1% |
| Epoch Capabilities Index | 100.58 | 112.21 |
| HellaSwag | 79.2% | 81% |
| PIQA | 80.1% | 83% |
| WinoGrande | 73% | 75.3% |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
| LAMBADA | 75.2% | — |
Math Llama 13b leads
Llama 13b: 26.7 (#256), Mistral 7B: 8.1 (#325)
| Benchmark | Llama 13b | Mistral 7B |
|---|---|---|
| LMArena Math | 838 | 1085 |
| GSM8K | 20.6% | 54.4% |
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| MATH Level 5 | — | 3.7% |
Knowledge Not comparable
Llama 13b: —, Mistral 7B: 7.4 (#311)
| Benchmark | Llama 13b | Mistral 7B |
|---|---|---|
| ARC (AI2) Challenge | 52.7% | 78.6% |
| BoolQ | 78.7% | 87.4% |
| MMLU | 47.7% | 62.5% |
| OpenBookQA | 56.4% | 79.8% |
| TriviaQA | 77.9% | 75.2% |
| GPQA Diamond | — | 15.2% |
| LMArena Expert | — | 1036 |
Multimodal Not comparable
Llama 13b: —, Mistral 7B: —
| Benchmark | Llama 13b | Mistral 7B |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Mistral 7B leads
Llama 13b: 16.6 (#297), Mistral 7B: 25.8 (#283)
| Benchmark | Llama 13b | Mistral 7B |
|---|---|---|
| LMArena Non-English | 819 | 1012 |
| LMArena Chinese | — | 1009 |
| LMArena French | — | 1037 |
| LMArena German | — | 987 |
| LMArena Japanese | — | 878 |
| LMArena Russian | — | 1018 |
| LMArena Spanish | — | 1026 |
Instruction Following Mistral 7B leads
Llama 13b: 36.7 (#305), Mistral 7B: 54.2 (#280)
| Benchmark | Llama 13b | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 781 | 1060 |
Long Context Not comparable
Llama 13b: —, Mistral 7B: 32.2 (#271)
| Benchmark | Llama 13b | Mistral 7B |
|---|---|---|
| LMArena Longer Query | — | 1060 |
Writing & Preference Mistral 7B leads
Llama 13b: 13.8 (#312), Mistral 7B: 30.7 (#286)
| Benchmark | Llama 13b | Mistral 7B |
|---|---|---|
| LMArena Text | 834 | 1090 |
| LMArena Creative Writing | 794 | 1068 |
| LMArena Multi-Turn | 753 | 1062 |
Frequently asked questions
Is Llama 13b better than Mistral 7B?
Llama 13b is the stronger model overall, scoring 24.4 to 23.0 on the Noometry Index.
Is Llama 13b or Mistral 7B better for coding?
Mistral 7B scores higher on coding benchmarks: 26.4 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and Mistral 7B share?
19 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Mistral 7B has 37.