Model comparison
Llama 3-70B vs Mistral 7B
Llama 3-70B is the stronger model overall, scoring 28.5 to 22.9 on the Noometry Index.
Last verified . 27 shared benchmarks.
Meta
Mistral AISummary
- They share 27 benchmarks with published results for both. Llama 3-70B scores higher in 8 categories and Mistral 7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3-70B leads 20.8 to 7.3.
- The biggest single-benchmark swing is BigCodeBench Complete: 54.5% for Llama 3-70B and 27.3% for Mistral 7B.
Side by side
| Llama 3-70B | Mistral 7B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 28.5 | 22.9 |
| Released | 2024-04-18 | 2023-09-27 |
| Weights | Open | Open |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.25 |
| Results tracked | 31 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Llama 3-70B: 35.3 (#215), Mistral 7B: 25.9 (#321)
| Benchmark | Llama 3-70B | Mistral 7B |
|---|---|---|
| BigCodeBench Instruct | 43.6% | 19.5% |
| LMArena Coding | 1206 | 1082 |
| BigCodeBench Complete | 54.5% | 27.3% |
| HumanEval+ | 72% | 36% |
| MBPP+ | 69% | 42.1% |
Agentic & Tool Use Not comparable
Llama 3-70B: 20.9 (#132), Mistral 7B: —
| Benchmark | Llama 3-70B | Mistral 7B |
|---|---|---|
| Cybench | 5% | — |
Reasoning Llama 3-70B leads
Llama 3-70B: 17.4 (#284), Mistral 7B: 12.6 (#331)
| Benchmark | Llama 3-70B | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1067 |
| DTBench | 54.2% | 42.5% |
| Epoch Capabilities Index | 122.91 | 111.97 |
| WinoGrande | 83.5% | 75.3% |
| Kagi LLM Benchmark | 35.1% | — |
| Chess Puzzles | — | 0% |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| ForecastBench | 57.1 | — |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
Math Llama 3-70B leads
Llama 3-70B: 12.0 (#299), Mistral 7B: 7.6 (#319)
| Benchmark | Llama 3-70B | Mistral 7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 0.3% |
| LMArena Math | 1218 | 1085 |
| MATH Level 5 | 22.6% | 3.7% |
| GSM8K | — | 54.4% |
Knowledge Llama 3-70B leads
Llama 3-70B: 20.8 (#272), Mistral 7B: 7.3 (#306)
| Benchmark | Llama 3-70B | Mistral 7B |
|---|---|---|
| GPQA Diamond | 40.6% | 15.2% |
| LMArena Expert | 1149 | 1036 |
| MMLU | 79.3% | 62.5% |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multilingual Llama 3-70B leads
Llama 3-70B: 33.8 (#246), Mistral 7B: 26.0 (#278)
| Benchmark | Llama 3-70B | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1142 | 1012 |
| LMArena Chinese | 1114 | 1009 |
| LMArena French | 1231 | 1036 |
| LMArena German | 1169 | 987 |
| LMArena Japanese | 1017 | 878 |
| LMArena Russian | 1159 | 1018 |
| LMArena Spanish | 1241 | 1026 |
| LMArena Korean | 1017 | — |
Instruction Following Llama 3-70B leads
Llama 3-70B: 62.8 (#233), Mistral 7B: 54.5 (#275)
| Benchmark | Llama 3-70B | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1194 | 1060 |
Long Context Llama 3-70B leads
Llama 3-70B: 35.6 (#235), Mistral 7B: 32.2 (#266)
| Benchmark | Llama 3-70B | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1174 | 1060 |
Writing & Preference Llama 3-70B leads
Llama 3-70B: 43.0 (#225), Mistral 7B: 30.9 (#281)
| Benchmark | Llama 3-70B | Mistral 7B |
|---|---|---|
| LMArena Text | 1221 | 1090 |
| LMArena Creative Writing | 1210 | 1068 |
| LMArena Multi-Turn | 1223 | 1062 |
Frequently asked questions
Is Llama 3-70B better than Mistral 7B?
Llama 3-70B is the stronger model overall, scoring 28.5 to 22.9 on the Noometry Index.
Is Llama 3-70B or Mistral 7B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.3 versus 25.9 in the Noometry coding category.
How many benchmarks do Llama 3-70B and Mistral 7B share?
27 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Mistral 7B has 37.