Model comparison
Codellama 34b Instruct vs Command R+
Command R+ is the stronger model overall, scoring 32.4 to 30.8 on the Noometry Index.
Last verified . 14 shared benchmarks.
Meta
CohereSummary
- They share 14 benchmarks with published results for both. Codellama 34b Instruct scores higher in 2 categories and Command R+ in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Command R+ leads 43.5 to 28.2.
Side by side
| Codellama 34b Instruct | Command R+ | |
|---|---|---|
| Provider | Meta | Cohere |
| Noometry Index | 30.8 | 32.4 |
| Released | — | 2024-08-30 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $10 |
| Results tracked | 14 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Codellama 34b Instruct: 28.5 (#314), Command R+: 29.1 (#309)
| Benchmark | Codellama 34b Instruct | Command R+ |
|---|---|---|
| BigCodeBench Instruct | 29% | 33.8% |
| LMArena Coding | 1046 | 1187 |
| BigCodeBench Complete | 37.1% | 41.9% |
| HumanEval+ | 43.9% | 56.7% |
| MBPP+ | 56.3% | 63.5% |
| LiveBench Coding | — | 19.1% |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 19.6 (#255), Command R+: 9.2 (#344)
| Benchmark | Codellama 34b Instruct | Command R+ |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1186 |
| SimpleBench | — | 17.4% |
| LiveBench Reasoning | — | 24.8% |
| DTBench | — | 54.9% |
| LiveBench Data Analysis | — | 38.1% |
| LMCA | — | 5% |
| Epoch Capabilities Index | — | 119.34 |
| LiveBench | — | 31.8% |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 31.0 (#230), Command R+: 28.9 (#242)
| Benchmark | Codellama 34b Instruct | Command R+ |
|---|---|---|
| LMArena Math | 1056 | 1188 |
| LiveBench Math | — | 21.3% |
Knowledge Not comparable
Codellama 34b Instruct: —, Command R+: 36.4 (#169)
| Benchmark | Codellama 34b Instruct | Command R+ |
|---|---|---|
| Vectara Hallucination Rate | — | 6.9% |
| LMArena Expert | — | 1174 |
| MMLU | — | 69.4% |
Multilingual Command R+ leads
Codellama 34b Instruct: 25.8 (#284), Command R+: 38.6 (#227)
| Benchmark | Codellama 34b Instruct | Command R+ |
|---|---|---|
| LMArena Non-English | 1011 | 1216 |
| LMArena Chinese | 976 | 1226 |
| LMArena French | — | 1209 |
| LMArena German | — | 1216 |
| LMArena Japanese | — | 1166 |
| LMArena Korean | — | 1138 |
| LMArena Russian | — | 1227 |
| LMArena Spanish | — | 1189 |
Instruction Following Command R+ leads
Codellama 34b Instruct: 52.2 (#291), Command R+: 60.0 (#254)
| Benchmark | Codellama 34b Instruct | Command R+ |
|---|---|---|
| LMArena Instruction Following | 1028 | 1197 |
| LiveBench Instruction Following | — | 57.6% |
Long Context Command R+ leads
Codellama 34b Instruct: 30.9 (#284), Command R+: 37.3 (#219)
| Benchmark | Codellama 34b Instruct | Command R+ |
|---|---|---|
| LMArena Longer Query | 1013 | 1230 |
Writing & Preference Command R+ leads
Codellama 34b Instruct: 28.2 (#297), Command R+: 43.5 (#228)
| Benchmark | Codellama 34b Instruct | Command R+ |
|---|---|---|
| LMArena Text | 1066 | 1229 |
| LMArena Creative Writing | 1032 | 1235 |
| LMArena Multi-Turn | 1015 | 1213 |
| LiveBench Language | — | 29.7% |
Frequently asked questions
Is Codellama 34b Instruct better than Command R+?
Command R+ is the stronger model overall, scoring 32.4 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or Command R+ better for coding?
They score almost the same on coding (28.5 vs 29.1); test both on your own repository before choosing.
How many benchmarks do Codellama 34b Instruct and Command R+ share?
14 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Command R+ has 34.