Model comparison
Command R vs DeepSeek LLM 67B
Command R is the stronger model overall, scoring 31.4 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
Cohere
DeepSeekSummary
- They share 10 benchmarks with published results for both. Command R scores higher in 6 categories and DeepSeek LLM 67B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command R leads 31.0 to 7.0.
Side by side
| Command R | DeepSeek LLM 67B | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 31.4 | 24.9 |
| Released | 2024-08-30 | 2023-11-29 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek LLM 67B leads
Command R: 29.3 (#306), DeepSeek LLM 67B: 31.9 (#278)
| Benchmark | Command R | DeepSeek LLM 67B |
|---|---|---|
| LMArena Coding | 1169 | 1096 |
| BigCodeBench Instruct | 37.1% | — |
| LiveBench Coding | 17.9% | — |
| BigCodeBench Complete | 45.2% | — |
Reasoning DeepSeek LLM 67B leads
Command R: 13.8 (#331), DeepSeek LLM 67B: 16.5 (#304)
| Benchmark | Command R | DeepSeek LLM 67B |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1070 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 21.9% | — |
| DTBench | 46.4% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| Epoch Capabilities Index | — | 110.5 |
| LiveBench | 27.5% | — |
Math Command R leads
Command R: 28.0 (#246), DeepSeek LLM 67B: 8.7 (#324)
| Benchmark | Command R | DeepSeek LLM 67B |
|---|---|---|
| LMArena Math | 1155 | 1108 |
| OTIS Mock AIME 2024-2025 | — | 0.8% |
| LiveBench Math | 19.4% | — |
| MATH Level 5 | — | 6.4% |
Knowledge Command R leads
Command R: 31.0 (#221), DeepSeek LLM 67B: 7.0 (#313)
| Benchmark | Command R | DeepSeek LLM 67B |
|---|---|---|
| GPQA Diamond | — | 24.6% |
| LMArena Expert | 1138 | — |
| MMLU | 65.2% | — |
Multilingual Command R leads
Command R: 35.7 (#245), DeepSeek LLM 67B: 29.4 (#267)
| Benchmark | Command R | DeepSeek LLM 67B |
|---|---|---|
| LMArena Non-English | 1174 | 1073 |
| LMArena Chinese | 1182 | 1132 |
| LMArena French | 1162 | — |
| LMArena German | 1176 | — |
| LMArena Japanese | 1143 | — |
| LMArena Korean | 1163 | — |
| LMArena Russian | 1174 | — |
| LMArena Spanish | 1151 | — |
Instruction Following Command R leads
Command R: 58.1 (#261), DeepSeek LLM 67B: 55.4 (#277)
| Benchmark | Command R | DeepSeek LLM 67B |
|---|---|---|
| LMArena Instruction Following | 1167 | 1079 |
| LiveBench Instruction Following | 55.6% | — |
Long Context Command R leads
Command R: 36.3 (#231), DeepSeek LLM 67B: 33.1 (#265)
| Benchmark | Command R | DeepSeek LLM 67B |
|---|---|---|
| LMArena Longer Query | 1198 | 1092 |
Writing & Preference Command R leads
Command R: 38.2 (#254), DeepSeek LLM 67B: 31.6 (#282)
| Benchmark | Command R | DeepSeek LLM 67B |
|---|---|---|
| LMArena Text | 1187 | 1105 |
| LMArena Creative Writing | 1170 | 1067 |
| LMArena Multi-Turn | 1163 | 1082 |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than DeepSeek LLM 67B?
Command R is the stronger model overall, scoring 31.4 to 24.9 on the Noometry Index.
Is Command R or DeepSeek LLM 67B better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 29.3 in the Noometry coding category.
How many benchmarks do Command R and DeepSeek LLM 67B share?
10 benchmarks have published results for both models. Command R has 29 scored results on Noometry and DeepSeek LLM 67B has 15.