Model comparison
Codellama 70b Instruct vs Mistral 7B
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 22.9 on the Noometry Index.
Last verified . 7 shared benchmarks.
Meta
Mistral AISummary
- They share 7 benchmarks with published results for both. Codellama 70b Instruct scores higher in 3 categories and Mistral 7B in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Codellama 70b Instruct leads 37.0 to 25.9.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 27.3% for Mistral 7B.
Side by side
| Codellama 70b Instruct | Mistral 7B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 33.3 | 22.9 |
| Released | — | 2023-09-27 |
| Weights | Open | Open |
| Context window | — | 8K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.25 |
| Results tracked | 7 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.0 (#189), Mistral 7B: 25.9 (#321)
| Benchmark | Codellama 70b Instruct | Mistral 7B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 19.5% |
| BigCodeBench Complete | 49.6% | 27.3% |
| HumanEval+ | 65.9% | 36% |
| LMArena Coding | — | 1082 |
| MBPP+ | — | 42.1% |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 19.2 (#241), Mistral 7B: 12.6 (#331)
| Benchmark | Codellama 70b Instruct | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1067 |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| Epoch Capabilities Index | — | 111.97 |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math Not comparable
Codellama 70b Instruct: —, Mistral 7B: 7.6 (#319)
| Benchmark | Codellama 70b Instruct | Mistral 7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| LMArena Math | — | 1085 |
| MATH Level 5 | — | 3.7% |
| GSM8K | — | 54.4% |
Knowledge Not comparable
Codellama 70b Instruct: —, Mistral 7B: 7.3 (#306)
| Benchmark | Codellama 70b Instruct | Mistral 7B |
|---|---|---|
| GPQA Diamond | — | 15.2% |
| LMArena Expert | — | 1036 |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multilingual Mistral 7B leads
Codellama 70b Instruct: 24.9 (#283), Mistral 7B: 26.0 (#278)
| Benchmark | Codellama 70b Instruct | Mistral 7B |
|---|---|---|
| LMArena Non-English | 992 | 1012 |
| LMArena Chinese | — | 1009 |
| LMArena French | — | 1036 |
| LMArena German | — | 987 |
| LMArena Japanese | — | 878 |
| LMArena Russian | — | 1018 |
| LMArena Spanish | — | 1026 |
Instruction Following Mistral 7B leads
Codellama 70b Instruct: 52.1 (#288), Mistral 7B: 54.5 (#275)
| Benchmark | Codellama 70b Instruct | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1060 |
Long Context Not comparable
Codellama 70b Instruct: —, Mistral 7B: 32.2 (#266)
| Benchmark | Codellama 70b Instruct | Mistral 7B |
|---|---|---|
| LMArena Longer Query | — | 1060 |
Writing & Preference Codellama 70b Instruct leads
Codellama 70b Instruct: 33.6 (#272), Mistral 7B: 30.9 (#281)
| Benchmark | Codellama 70b Instruct | Mistral 7B |
|---|---|---|
| LMArena Text | 1057 | 1090 |
| LMArena Creative Writing | — | 1068 |
| LMArena Multi-Turn | — | 1062 |
Frequently asked questions
Is Codellama 70b Instruct better than Mistral 7B?
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 22.9 on the Noometry Index.
Is Codellama 70b Instruct or Mistral 7B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 25.9 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Mistral 7B share?
7 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Mistral 7B has 37.