Model comparison
Command R+ vs Deepseek Coder v2
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 32.4 on the Noometry Index.
Last verified . 21 shared benchmarks.
Cohere
DeepSeekSummary
- They share 21 benchmarks with published results for both. Command R+ scores higher in 4 categories and Deepseek Coder v2 in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Deepseek Coder v2 leads 23.6 to 9.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 41.9% for Command R+ and 59.7% for Deepseek Coder v2.
Side by side
| Command R+ | Deepseek Coder v2 | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 32.4 | 35.9 |
| Released | 2024-08-30 | 2024-06-17 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 34 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Command R+: 29.1 (#309), Deepseek Coder v2: 38.1 (#183)
| Benchmark | Command R+ | Deepseek Coder v2 |
|---|---|---|
| BigCodeBench Instruct | 33.8% | 48.2% |
| LMArena Coding | 1187 | 1251 |
| BigCodeBench Complete | 41.9% | 59.7% |
| HumanEval+ | 56.7% | 82.3% |
| MBPP+ | 63.5% | 75.1% |
| LiveBench Coding | 19.1% | — |
Reasoning Deepseek Coder v2 leads
Command R+: 9.2 (#344), Deepseek Coder v2: 23.6 (#176)
| Benchmark | Command R+ | Deepseek Coder v2 |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1207 |
| 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% | — |
| WinoGrande | — | 83.7% |
Math Deepseek Coder v2 leads
Command R+: 28.9 (#242), Deepseek Coder v2: 34.9 (#190)
| Benchmark | Command R+ | Deepseek Coder v2 |
|---|---|---|
| LMArena Math | 1188 | 1241 |
| LiveBench Math | 21.3% | — |
| GSM8K | — | 94.5% |
Knowledge Command R+ leads
Command R+: 36.4 (#169), Deepseek Coder v2: 32.3 (#212)
| Benchmark | Command R+ | Deepseek Coder v2 |
|---|---|---|
| LMArena Expert | 1174 | 1181 |
| Vectara Hallucination Rate | 6.9% | — |
| ARC (AI2) Challenge | — | 64.3% |
| MMLU | 69.4% | — |
Multilingual Command R+ leads
Command R+: 38.6 (#227), Deepseek Coder v2: 36.3 (#240)
| Benchmark | Command R+ | Deepseek Coder v2 |
|---|---|---|
| LMArena Non-English | 1216 | 1182 |
| LMArena Chinese | 1226 | 1201 |
| LMArena French | 1209 | 1185 |
| LMArena German | 1216 | 1164 |
| LMArena Japanese | 1166 | 1126 |
| LMArena Korean | 1138 | 1104 |
| LMArena Russian | 1227 | 1188 |
| LMArena Spanish | 1189 | 1153 |
Instruction Following Deepseek Coder v2 leads
Command R+: 60.0 (#254), Deepseek Coder v2: 61.7 (#242)
| Benchmark | Command R+ | Deepseek Coder v2 |
|---|---|---|
| LMArena Instruction Following | 1197 | 1180 |
| LiveBench Instruction Following | 57.6% | — |
Long Context Too close to call
Command R+: 37.3 (#219), Deepseek Coder v2: 37.0 (#224)
| Benchmark | Command R+ | Deepseek Coder v2 |
|---|---|---|
| LMArena Longer Query | 1230 | 1219 |
Writing & Preference Command R+ leads
Command R+: 43.5 (#228), Deepseek Coder v2: 38.2 (#253)
| Benchmark | Command R+ | Deepseek Coder v2 |
|---|---|---|
| LMArena Text | 1229 | 1191 |
| LMArena Creative Writing | 1235 | 1120 |
| LMArena Multi-Turn | 1213 | 1177 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Deepseek Coder v2?
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 32.4 on the Noometry Index.
Is Command R+ or Deepseek Coder v2 better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 29.1 in the Noometry coding category.
How many benchmarks do Command R+ and Deepseek Coder v2 share?
21 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Deepseek Coder v2 has 24.