Model comparison
Codellama 70b Instruct vs Command R+
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 32.0 on the Noometry Index.
Last verified . 7 shared benchmarks.
Meta
CohereSummary
- They share 7 benchmarks with published results for both. Codellama 70b Instruct scores higher in 2 categories and Command R+ in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Command R+ leads 38.8 to 24.9.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 41.9% for Command R+.
Side by side
| Codellama 70b Instruct | Command R+ | |
|---|---|---|
| Provider | Meta | Cohere |
| Noometry Index | 33.3 | 32.0 |
| Released | — | 2024-08-30 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $10 |
| 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: 37.0 (#189), Command R+: 28.6 (#304)
| Benchmark | Codellama 70b Instruct | Command R+ |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 33.8% |
| BigCodeBench Complete | 49.6% | 41.9% |
| HumanEval+ | 65.9% | 56.7% |
| LiveBench Coding | — | 19.1% |
| LMArena Coding | — | 1187 |
| MBPP+ | — | 63.5% |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 19.2 (#241), Command R+: 8.9 (#341)
| Benchmark | Codellama 70b Instruct | Command R+ |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1186 |
| SimpleBench | — | 17.4% |
| LiveBench Reasoning | — | 24.8% |
| DTBench | — | 54.9% |
| LiveBench Data Analysis | — | 38.1% |
| LMCA | — | 5% |
| Epoch Capabilities Index | — | 119.28 |
| LiveBench | — | 31.8% |
Math Not comparable
Codellama 70b Instruct: —, Command R+: 26.6 (#239)
| Benchmark | Codellama 70b Instruct | Command R+ |
|---|---|---|
| LiveBench Math | — | 21.3% |
| LMArena Math | — | 1188 |
Knowledge Not comparable
Codellama 70b Instruct: —, Command R+: 35.9 (#165)
| Benchmark | Codellama 70b Instruct | Command R+ |
|---|---|---|
| Vectara Hallucination Rate | — | 6.9% |
| LMArena Expert | — | 1174 |
| MMLU | — | 69.4% |
Multilingual Command R+ leads
Codellama 70b Instruct: 24.9 (#283), Command R+: 38.8 (#222)
| Benchmark | Codellama 70b Instruct | Command R+ |
|---|---|---|
| LMArena Non-English | 992 | 1216 |
| LMArena Chinese | — | 1226 |
| LMArena French | — | 1208 |
| LMArena German | — | 1216 |
| LMArena Japanese | — | 1166 |
| LMArena Korean | — | 1138 |
| LMArena Russian | — | 1227 |
| LMArena Spanish | — | 1189 |
Instruction Following Command R+ leads
Codellama 70b Instruct: 52.1 (#288), Command R+: 60.2 (#249)
| Benchmark | Codellama 70b Instruct | Command R+ |
|---|---|---|
| LMArena Instruction Following | 1024 | 1197 |
| LiveBench Instruction Following | — | 57.6% |
Long Context Not comparable
Codellama 70b Instruct: —, Command R+: 37.3 (#214)
| Benchmark | Codellama 70b Instruct | Command R+ |
|---|---|---|
| LMArena Longer Query | — | 1231 |
Writing & Preference Command R+ leads
Codellama 70b Instruct: 33.6 (#272), Command R+: 43.7 (#223)
| Benchmark | Codellama 70b Instruct | Command R+ |
|---|---|---|
| LMArena Text | 1057 | 1229 |
| LMArena Creative Writing | — | 1235 |
| LMArena Multi-Turn | — | 1213 |
| LiveBench Language | — | 29.7% |
Frequently asked questions
Is Codellama 70b Instruct better than Command R+?
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 32.0 on the Noometry Index.
Is Codellama 70b Instruct or Command R+ better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 28.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Command R+ share?
7 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Command R+ has 34.