Model comparison
Command R+ vs DeepSeek Coder 33B
Command R+ has enough public results to be ranked (#251); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Last verified . 6 shared benchmarks.
Cohere
DeepSeekSummary
- They share 6 benchmarks with published results for both. Command R+ scores higher in 0 categories and DeepSeek Coder 33B in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 33B leads 37.4 to 28.6.
- The biggest single-benchmark swing is BigCodeBench Complete: 41.9% for Command R+ and 51.1% for DeepSeek Coder 33B.
Side by side
| Command R+ | DeepSeek Coder 33B | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 32.0 | 38.3 |
| Released | 2024-08-30 | 2023-11-02 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 34 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek Coder 33B leads
Command R+: 28.6 (#304), DeepSeek Coder 33B: 37.4 (#180)
| Benchmark | Command R+ | DeepSeek Coder 33B |
|---|---|---|
| BigCodeBench Instruct | 33.8% | 42% |
| BigCodeBench Complete | 41.9% | 51.1% |
| HumanEval+ | 56.7% | 75% |
| MBPP+ | 63.5% | 70.1% |
| LiveBench Coding | 19.1% | — |
| LMArena Coding | 1187 | — |
Reasoning Not comparable
Command R+: 8.9 (#341), DeepSeek Coder 33B: —
| Benchmark | Command R+ | DeepSeek Coder 33B |
|---|---|---|
| Epoch Capabilities Index | 119.28 | 95.74 |
| SimpleBench | 17.4% | — |
| LiveBench Reasoning | 24.8% | — |
| LMArena Hard Prompts | 1186 | — |
| DTBench | 54.9% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| LiveBench | 31.8% | — |
| WinoGrande | — | 62% |
Math Not comparable
Command R+: 26.6 (#239), DeepSeek Coder 33B: —
| Benchmark | Command R+ | DeepSeek Coder 33B |
|---|---|---|
| LiveBench Math | 21.3% | — |
| LMArena Math | 1188 | — |
| GSM8K | — | 35.4% |
Knowledge Not comparable
Command R+: 35.9 (#165), DeepSeek Coder 33B: —
| Benchmark | Command R+ | DeepSeek Coder 33B |
|---|---|---|
| MMLU | 69.4% | 39.4% |
| Vectara Hallucination Rate | 6.9% | — |
| LMArena Expert | 1174 | — |
| ARC (AI2) Challenge | — | 42.2% |
Multilingual Not comparable
Command R+: 38.8 (#222), DeepSeek Coder 33B: —
| Benchmark | Command R+ | DeepSeek Coder 33B |
|---|---|---|
| LMArena Non-English | 1216 | — |
| LMArena Chinese | 1226 | — |
| LMArena French | 1208 | — |
| LMArena German | 1216 | — |
| LMArena Japanese | 1166 | — |
| LMArena Korean | 1138 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1189 | — |
Instruction Following Not comparable
Command R+: 60.2 (#249), DeepSeek Coder 33B: —
| Benchmark | Command R+ | DeepSeek Coder 33B |
|---|---|---|
| LiveBench Instruction Following | 57.6% | — |
| LMArena Instruction Following | 1197 | — |
Long Context Not comparable
Command R+: 37.3 (#214), DeepSeek Coder 33B: —
| Benchmark | Command R+ | DeepSeek Coder 33B |
|---|---|---|
| LMArena Longer Query | 1231 | — |
Writing & Preference Not comparable
Command R+: 43.7 (#223), DeepSeek Coder 33B: —
| Benchmark | Command R+ | DeepSeek Coder 33B |
|---|---|---|
| LMArena Text | 1229 | — |
| LMArena Creative Writing | 1235 | — |
| LMArena Multi-Turn | 1213 | — |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than DeepSeek Coder 33B?
Command R+ has enough public results to be ranked (#251); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Is Command R+ or DeepSeek Coder 33B better for coding?
DeepSeek Coder 33B scores higher on coding benchmarks: 37.4 versus 28.6 in the Noometry coding category.
How many benchmarks do Command R+ and DeepSeek Coder 33B share?
6 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and DeepSeek Coder 33B has 9.