Model comparison
Command R vs DeepSeek-R1-Distill-Qwen-32B
DeepSeek-R1-Distill-Qwen-32B is the stronger model overall, scoring 35.5 to 31.4 on the Noometry Index.
Last verified . 9 shared benchmarks.
Cohere
DeepSeekSummary
- They share 9 benchmarks with published results for both. Command R scores higher in 0 categories and DeepSeek-R1-Distill-Qwen-32B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-R1-Distill-Qwen-32B leads 49.6 to 38.2.
- The biggest single-benchmark swing is LiveBench Math: 19.4% for Command R and 59.4% for DeepSeek-R1-Distill-Qwen-32B.
Side by side
| Command R | DeepSeek-R1-Distill-Qwen-32B | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 31.4 | 35.5 |
| Released | 2024-08-30 | 2025-01-20 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1-Distill-Qwen-32B leads
Command R: 29.3 (#306), DeepSeek-R1-Distill-Qwen-32B: 36.1 (#212)
| Benchmark | Command R | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| BigCodeBench Instruct | 37.1% | 43.9% |
| LiveBench Coding | 17.9% | 33.7% |
| BigCodeBench Complete | 45.2% | 54.9% |
| LMArena Coding | 1169 | — |
Agentic & Tool Use Not comparable
Command R: —, DeepSeek-R1-Distill-Qwen-32B: 28.1 (#94)
| Benchmark | Command R | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| BALROG | — | 19.5% |
Reasoning DeepSeek-R1-Distill-Qwen-32B leads
Command R: 13.8 (#331), DeepSeek-R1-Distill-Qwen-32B: 18.2 (#284)
| Benchmark | Command R | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LiveBench Reasoning | 21.9% | 52.3% |
| LiveBench Data Analysis | 33.3% | 45.4% |
| LiveBench | 27.5% | 45.5% |
| Chess Puzzles | — | 1% |
| LMArena Hard Prompts | 1164 | — |
| DTBench | 46.4% | — |
| LMCA | 9.2% | — |
| Epoch Capabilities Index | — | 137.44 |
Math DeepSeek-R1-Distill-Qwen-32B leads
Command R: 28.0 (#246), DeepSeek-R1-Distill-Qwen-32B: 34.5 (#194)
| Benchmark | Command R | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LiveBench Math | 19.4% | 59.4% |
| OTIS Mock AIME 2024-2025 | — | 55.6% |
| LMArena Math | 1155 | — |
Knowledge DeepSeek-R1-Distill-Qwen-32B leads
Command R: 31.0 (#221), DeepSeek-R1-Distill-Qwen-32B: 35.7 (#182)
| Benchmark | Command R | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| GPQA Diamond | — | 64.1% |
| LMArena Expert | 1138 | — |
| MMLU | 65.2% | — |
Multilingual Not comparable
Command R: 35.7 (#245), DeepSeek-R1-Distill-Qwen-32B: —
| Benchmark | Command R | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LMArena Non-English | 1174 | — |
| LMArena Chinese | 1182 | — |
| LMArena French | 1162 | — |
| LMArena German | 1176 | — |
| LMArena Japanese | 1143 | — |
| LMArena Korean | 1163 | — |
| LMArena Russian | 1174 | — |
| LMArena Spanish | 1151 | — |
Instruction Following DeepSeek-R1-Distill-Qwen-32B leads
Command R: 58.1 (#261), DeepSeek-R1-Distill-Qwen-32B: 61.6 (#243)
| Benchmark | Command R | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LiveBench Instruction Following | 55.6% | 55.7% |
| LMArena Instruction Following | 1167 | — |
Long Context Not comparable
Command R: 36.3 (#231), DeepSeek-R1-Distill-Qwen-32B: —
| Benchmark | Command R | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LMArena Longer Query | 1198 | — |
Writing & Preference DeepSeek-R1-Distill-Qwen-32B leads
Command R: 38.2 (#254), DeepSeek-R1-Distill-Qwen-32B: 49.6 (#188)
| Benchmark | Command R | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LiveBench Language | 16.7% | 26.8% |
| LMArena Text | 1187 | — |
| LMArena Creative Writing | 1170 | — |
| LMArena Multi-Turn | 1163 | — |
Frequently asked questions
Is Command R better than DeepSeek-R1-Distill-Qwen-32B?
DeepSeek-R1-Distill-Qwen-32B is the stronger model overall, scoring 35.5 to 31.4 on the Noometry Index.
Is Command R or DeepSeek-R1-Distill-Qwen-32B better for coding?
DeepSeek-R1-Distill-Qwen-32B scores higher on coding benchmarks: 36.1 versus 29.3 in the Noometry coding category.
How many benchmarks do Command R and DeepSeek-R1-Distill-Qwen-32B share?
9 benchmarks have published results for both models. Command R has 29 scored results on Noometry and DeepSeek-R1-Distill-Qwen-32B has 14.