Model comparison
Codellama 70b Instruct vs Mixtral 8x22B
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 27.1 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 2 categories and Mixtral 8x22B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where Codellama 70b Instruct leads 37.6 to 24.2.
Side by side
| Codellama 70b Instruct | Mixtral 8x22B | |
|---|---|---|
| Provider | Meta | Mistral AI |
| Noometry Index | 33.7 | 27.1 |
| Released | — | 2024-04-17 |
| Weights | Open | Open |
| Context window | — | 64K |
| Max output | — | 64K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 7 | 34 |
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), Mixtral 8x22B: 24.2 (#329)
| Benchmark | Codellama 70b Instruct | Mixtral 8x22B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 40.6% |
| BigCodeBench Complete | 49.6% | 50.2% |
| HumanEval+ | 65.9% | 72% |
| WeirdML | — | 3.2% |
| LMArena Coding | — | 1166 |
| MBPP+ | — | 64.3% |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Mixtral 8x22B: 23.1 (#127)
| Benchmark | Codellama 70b Instruct | Mixtral 8x22B |
|---|---|---|
| Cybench | — | 7.5% |
Reasoning Too close to call
Codellama 70b Instruct: 20.1 (#242), Mixtral 8x22B: 19.9 (#248)
| Benchmark | Codellama 70b Instruct | Mixtral 8x22B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1150 |
| DTBench | — | 55.1% |
| Epoch Capabilities Index | — | 122.03 |
| ForecastBench | — | 56.3 |
Math Not comparable
Codellama 70b Instruct: —, Mixtral 8x22B: 22.9 (#275)
| Benchmark | Codellama 70b Instruct | Mixtral 8x22B |
|---|---|---|
| Omni-MATH | — | 16.3% |
| LMArena Math | — | 1184 |
| MATH Level 5 | — | 24.2% |
Knowledge Not comparable
Codellama 70b Instruct: —, Mixtral 8x22B: 15.1 (#293)
| Benchmark | Codellama 70b Instruct | Mixtral 8x22B |
|---|---|---|
| GPQA Diamond | — | 34.1% |
| MMLU-Pro | — | 46% |
| GPQA (HELM) | — | 33.4% |
| LMArena Expert | — | 1113 |
| MMLU | — | 77.8% |
Multilingual Mixtral 8x22B leads
Codellama 70b Instruct: 24.8 (#288), Mixtral 8x22B: 32.8 (#255)
| Benchmark | Codellama 70b Instruct | Mixtral 8x22B |
|---|---|---|
| LMArena Non-English | 992 | 1128 |
| LMArena Chinese | — | 1116 |
| LMArena French | — | 1166 |
| LMArena German | — | 1141 |
| LMArena Japanese | — | 1037 |
| LMArena Korean | — | 1057 |
| LMArena Russian | — | 1158 |
| LMArena Spanish | — | 1151 |
Instruction Following Mixtral 8x22B leads
Codellama 70b Instruct: 51.9 (#293), Mixtral 8x22B: 57.7 (#266)
| Benchmark | Codellama 70b Instruct | Mixtral 8x22B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1147 |
| IFEval | — | 72.4% |
Long Context Not comparable
Codellama 70b Instruct: —, Mixtral 8x22B: 34.7 (#247)
| Benchmark | Codellama 70b Instruct | Mixtral 8x22B |
|---|---|---|
| LMArena Longer Query | — | 1144 |
Writing & Preference Mixtral 8x22B leads
Codellama 70b Instruct: 33.4 (#277), Mixtral 8x22B: 36.9 (#262)
| Benchmark | Codellama 70b Instruct | Mixtral 8x22B |
|---|---|---|
| LMArena Text | 1057 | 1162 |
| LMArena Creative Writing | — | 1141 |
| WildBench | — | 71.1% |
| LMArena Multi-Turn | — | 1130 |
Frequently asked questions
Is Codellama 70b Instruct better than Mixtral 8x22B?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 27.1 on the Noometry Index.
Is Codellama 70b Instruct or Mixtral 8x22B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 24.2 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Mixtral 8x22B share?
7 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Mixtral 8x22B has 34.