Model comparison
Llama 2-13B vs Mistral 7B
Llama 2-13B is the stronger model overall, scoring 29.6 to 23.0 on the Noometry Index.
Last verified . 29 shared benchmarks.
Meta
Mistral AISummary
- They share 29 benchmarks with published results for both. Llama 2-13B scores higher in 5 categories and Mistral 7B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 2-13B leads 31.1 to 8.1.
Side by side
| Llama 2-13B | Mistral 7B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 29.6 | 23.0 |
| Released | 2023-07-18 | 2023-09-27 |
| Weights | Open | Open |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.25 |
| Results tracked | 32 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-13B leads
Llama 2-13B: 30.9 (#291), Mistral 7B: 26.4 (#326)
| Benchmark | Llama 2-13B | Mistral 7B |
|---|---|---|
| LMArena Coding | 1062 | 1082 |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Reasoning Too close to call
Llama 2-13B: 12.8 (#337), Mistral 7B: 13.1 (#336)
| Benchmark | Llama 2-13B | Mistral 7B |
|---|---|---|
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1051 | 1067 |
| DTBench | 42.2% | 42.5% |
| BIG-Bench Hard | 58.2% | 56.1% |
| Epoch Capabilities Index | 106.17 | 112.21 |
| HellaSwag | 80.7% | 81% |
| PIQA | 80.8% | 83% |
| WinoGrande | 72.8% | 75.3% |
| Adversarial NLI | — | 47.1% |
| LAMBADA | 76.5% | — |
Math Llama 2-13B leads
Llama 2-13B: 31.1 (#229), Mistral 7B: 8.1 (#325)
| Benchmark | Llama 2-13B | Mistral 7B |
|---|---|---|
| LMArena Math | 1065 | 1085 |
| GSM8K | 36.9% | 54.4% |
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| MATH Level 5 | — | 3.7% |
Knowledge Llama 2-13B leads
Llama 2-13B: 28.1 (#249), Mistral 7B: 7.4 (#311)
| Benchmark | Llama 2-13B | Mistral 7B |
|---|---|---|
| LMArena Expert | 1030 | 1036 |
| ARC (AI2) Challenge | 60.3% | 78.6% |
| BoolQ | 82.4% | 87.4% |
| MMLU | 55.6% | 62.5% |
| OpenBookQA | 57% | 79.8% |
| TriviaQA | 79.6% | 75.2% |
| GPQA Diamond | — | 15.2% |
Multimodal Not comparable
Llama 2-13B: —, Mistral 7B: —
| Benchmark | Llama 2-13B | Mistral 7B |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual Too close to call
Llama 2-13B: 26.5 (#279), Mistral 7B: 25.8 (#283)
| Benchmark | Llama 2-13B | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1024 | 1012 |
| LMArena Chinese | 1001 | 1009 |
| LMArena French | 1044 | 1037 |
| LMArena German | 1009 | 987 |
| LMArena Japanese | 894 | 878 |
| LMArena Russian | 1055 | 1018 |
| LMArena Spanish | 1087 | 1026 |
| LMArena Korean | 953 | — |
Instruction Following Too close to call
Llama 2-13B: 53.3 (#287), Mistral 7B: 54.2 (#280)
| Benchmark | Llama 2-13B | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1045 | 1060 |
Long Context Too close to call
Llama 2-13B: 32.3 (#269), Mistral 7B: 32.2 (#271)
| Benchmark | Llama 2-13B | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1064 | 1060 |
Writing & Preference Too close to call
Llama 2-13B: 29.8 (#289), Mistral 7B: 30.7 (#286)
| Benchmark | Llama 2-13B | Mistral 7B |
|---|---|---|
| LMArena Text | 1084 | 1090 |
| LMArena Creative Writing | 1047 | 1068 |
| LMArena Multi-Turn | 1050 | 1062 |
Frequently asked questions
Is Llama 2-13B better than Mistral 7B?
Llama 2-13B is the stronger model overall, scoring 29.6 to 23.0 on the Noometry Index.
Is Llama 2-13B or Mistral 7B better for coding?
Llama 2-13B scores higher on coding benchmarks: 30.9 versus 26.4 in the Noometry coding category.
How many benchmarks do Llama 2-13B and Mistral 7B share?
29 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Mistral 7B has 37.