Model comparison
Codellama 34b Instruct vs Mistral 7B
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 23.0 on the Noometry Index.
Last verified . 14 shared benchmarks.
Meta
Mistral AISummary
- They share 14 benchmarks with published results for both. Codellama 34b Instruct scores higher in 3 categories and Mistral 7B in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Codellama 34b Instruct leads 31.0 to 8.1.
- The biggest single-benchmark swing is BigCodeBench Complete: 37.1% for Codellama 34b Instruct and 27.3% for Mistral 7B.
Side by side
| Codellama 34b Instruct | Mistral 7B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.8 | 23.0 |
| 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 | 14 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 34b Instruct leads
Codellama 34b Instruct: 28.5 (#314), Mistral 7B: 26.4 (#326)
| Benchmark | Codellama 34b Instruct | Mistral 7B |
|---|---|---|
| BigCodeBench Instruct | 29% | 19.5% |
| LMArena Coding | 1046 | 1082 |
| BigCodeBench Complete | 37.1% | 27.3% |
| HumanEval+ | 43.9% | 36% |
| MBPP+ | 56.3% | 42.1% |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 19.6 (#255), Mistral 7B: 13.1 (#336)
| Benchmark | Codellama 34b Instruct | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1067 |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| Epoch Capabilities Index | — | 112.21 |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 31.0 (#230), Mistral 7B: 8.1 (#325)
| Benchmark | Codellama 34b Instruct | Mistral 7B |
|---|---|---|
| LMArena Math | 1056 | 1085 |
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| MATH Level 5 | — | 3.7% |
| GSM8K | — | 54.4% |
Knowledge Not comparable
Codellama 34b Instruct: —, Mistral 7B: 7.4 (#311)
| Benchmark | Codellama 34b 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 Too close to call
Codellama 34b Instruct: 25.8 (#284), Mistral 7B: 25.8 (#283)
| Benchmark | Codellama 34b Instruct | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1011 | 1012 |
| LMArena Chinese | 976 | 1009 |
| LMArena French | — | 1037 |
| LMArena German | — | 987 |
| LMArena Japanese | — | 878 |
| LMArena Russian | — | 1018 |
| LMArena Spanish | — | 1026 |
Instruction Following Mistral 7B leads
Codellama 34b Instruct: 52.2 (#291), Mistral 7B: 54.2 (#280)
| Benchmark | Codellama 34b Instruct | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1060 |
Long Context Mistral 7B leads
Codellama 34b Instruct: 30.9 (#284), Mistral 7B: 32.2 (#271)
| Benchmark | Codellama 34b Instruct | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1013 | 1060 |
Writing & Preference Mistral 7B leads
Codellama 34b Instruct: 28.2 (#297), Mistral 7B: 30.7 (#286)
| Benchmark | Codellama 34b Instruct | Mistral 7B |
|---|---|---|
| LMArena Text | 1066 | 1090 |
| LMArena Creative Writing | 1032 | 1068 |
| LMArena Multi-Turn | 1015 | 1062 |
Frequently asked questions
Is Codellama 34b Instruct better than Mistral 7B?
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 23.0 on the Noometry Index.
Is Codellama 34b Instruct or Mistral 7B better for coding?
Codellama 34b Instruct scores higher on coding benchmarks: 28.5 versus 26.4 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Mistral 7B share?
14 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Mistral 7B has 37.