Model comparison
Codellama 70b Instruct vs Mistral
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 29.9 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
Mistral AISummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and Mistral in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Mistral leads 32.8 to 24.8.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | Mistral | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 33.7 | 29.9 |
| Released | — | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.6 (#193), Mistral: 33.8 (#250)
| Benchmark | Codellama 70b Instruct | Mistral |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1162 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Mistral leads
Codellama 70b Instruct: 20.1 (#242), Mistral: 22.2 (#200)
| Benchmark | Codellama 70b Instruct | Mistral |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1149 |
Math Not comparable
Codellama 70b Instruct: —, Mistral: 22.3 (#278)
| Benchmark | Codellama 70b Instruct | Mistral |
|---|---|---|
| Omni-MATH | — | 7.2% |
| LMArena Math | — | 1180 |
Knowledge Not comparable
Codellama 70b Instruct: —, Mistral: 16.6 (#288)
| Benchmark | Codellama 70b Instruct | Mistral |
|---|---|---|
| MMLU-Pro | — | 27.7% |
| GPQA (HELM) | — | 30.3% |
| LMArena Expert | — | 1125 |
Multilingual Mistral leads
Codellama 70b Instruct: 24.8 (#288), Mistral: 32.8 (#254)
| Benchmark | Codellama 70b Instruct | Mistral |
|---|---|---|
| LMArena Non-English | 992 | 1129 |
| LMArena Chinese | — | 1109 |
| LMArena French | — | 1180 |
| LMArena German | — | 1155 |
| LMArena Japanese | — | 1013 |
| LMArena Korean | — | 1032 |
| LMArena Russian | — | 1168 |
| LMArena Spanish | — | 1143 |
Instruction Following Too close to call
Codellama 70b Instruct: 51.9 (#293), Mistral: 52.6 (#288)
| Benchmark | Codellama 70b Instruct | Mistral |
|---|---|---|
| LMArena Instruction Following | 1024 | 1152 |
| IFEval | — | 56.8% |
Long Context Not comparable
Codellama 70b Instruct: —, Mistral: 35.0 (#245)
| Benchmark | Codellama 70b Instruct | Mistral |
|---|---|---|
| LMArena Longer Query | — | 1153 |
Writing & Preference Mistral leads
Codellama 70b Instruct: 33.4 (#277), Mistral: 37.0 (#260)
| Benchmark | Codellama 70b Instruct | Mistral |
|---|---|---|
| LMArena Text | 1057 | 1165 |
| LMArena Creative Writing | — | 1158 |
| WildBench | — | 66% |
| LMArena Multi-Turn | — | 1147 |
Frequently asked questions
Is Codellama 70b Instruct better than Mistral?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 29.9 on the Noometry Index.
Is Codellama 70b Instruct or Mistral better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 33.8 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Mistral share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Mistral has 22.