Model comparison
Codellama 34b Instruct vs Mistral
Codellama 34b Instruct and Mistral score almost the same on the Noometry Index (30.2 vs 29.4), so choose on price, context window or the category you care about most.
Last verified . 10 shared benchmarks.
Meta
Mistral AISummary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 1 category and Mistral in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral leads 37.2 to 28.4.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 34b Instruct | Mistral | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 30.2 | 29.4 |
| Released | — | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral leads
Codellama 34b Instruct: 28.0 (#310), Mistral: 33.2 (#249)
| Benchmark | Codellama 34b Instruct | Mistral |
|---|---|---|
| LMArena Coding | 1046 | 1162 |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Mistral leads
Codellama 34b Instruct: 18.8 (#250), Mistral: 21.3 (#199)
| Benchmark | Codellama 34b Instruct | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1149 |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 28.5 (#227), Mistral: 20.5 (#275)
| Benchmark | Codellama 34b Instruct | Mistral |
|---|---|---|
| LMArena Math | 1056 | 1180 |
| Omni-MATH | — | 7.2% |
Knowledge Not comparable
Codellama 34b Instruct: —, Mistral: 16.3 (#283)
| Benchmark | Codellama 34b Instruct | Mistral |
|---|---|---|
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| LMArena Expert | — | 1125 |
Multilingual Mistral leads
Codellama 34b Instruct: 25.9 (#279), Mistral: 33.0 (#249)
| Benchmark | Codellama 34b Instruct | Mistral |
|---|---|---|
| LMArena Non-English | 1011 | 1129 |
| LMArena Chinese | 976 | 1109 |
| LMArena French | — | 1179 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1012 |
| LMArena Korean | — | 1032 |
| LMArena Russian | — | 1168 |
| LMArena Spanish | — | 1143 |
Instruction Following Too close to call
Codellama 34b Instruct: 52.4 (#286), Mistral: 52.9 (#283)
| Benchmark | Codellama 34b Instruct | Mistral |
|---|---|---|
| LMArena Instruction Following | 1028 | 1152 |
| IFEval | — | 56.8% |
Long Context Mistral leads
Codellama 34b Instruct: 30.8 (#279), Mistral: 35.0 (#240)
| Benchmark | Codellama 34b Instruct | Mistral |
|---|---|---|
| LMArena Longer Query | 1014 | 1154 |
Writing & Preference Mistral leads
Codellama 34b Instruct: 28.4 (#292), Mistral: 37.2 (#255)
| Benchmark | Codellama 34b Instruct | Mistral |
|---|---|---|
| LMArena Text | 1066 | 1165 |
| LMArena Creative Writing | 1032 | 1158 |
| LMArena Multi-Turn | 1015 | 1147 |
| WildBench | — | 66% |
Frequently asked questions
Is Codellama 34b Instruct better than Mistral?
Codellama 34b Instruct and Mistral score almost the same on the Noometry Index (30.2 vs 29.4), so choose on price, context window or the category you care about most.
Is Codellama 34b Instruct or Mistral better for coding?
Mistral scores higher on coding benchmarks: 33.2 versus 28.0 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Mistral share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Mistral has 22.