Model comparison
Command A vs DeepSeek-R1-Distill-Llama-70B
DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.4 to 35.9 on the Noometry Index.
Last verified . 1 shared benchmarks.
Cohere
DeepSeekSummary
- They share 1 benchmark with published results for both. Command A scores higher in 2 categories and DeepSeek-R1-Distill-Llama-70B in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-R1-Distill-Llama-70B leads 36.3 to 26.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 28.8% for Command A and 52.3% for DeepSeek-R1-Distill-Llama-70B.
Side by side
| Command A | DeepSeek-R1-Distill-Llama-70B | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 35.9 | 37.4 |
| Released | 2025-03-13 | 2025-01-20 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1-Distill-Llama-70B leads
Command A: 26.8 (#317), DeepSeek-R1-Distill-Llama-70B: 36.3 (#197)
| Benchmark | Command A | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| Aider Polyglot | 12% | — |
| BigCodeBench Instruct | — | 35.3% |
| LiveBench Coding | — | 51.6% |
| LMArena Coding | 1331 | — |
| BigCodeBench Complete | — | 49.9% |
Agentic & Tool Use Not comparable
Command A: 35.7 (#36), DeepSeek-R1-Distill-Llama-70B: —
| Benchmark | Command A | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning DeepSeek-R1-Distill-Llama-70B leads
Command A: 17.7 (#276), DeepSeek-R1-Distill-Llama-70B: 24.1 (#150)
| Benchmark | Command A | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 52.3% |
| LiveBench Reasoning | — | 67.6% |
| LMArena Hard Prompts | 1326 | — |
| DTBench | 61.3% | — |
| LiveBench Data Analysis | — | 55.9% |
| LMCA | 10.3% | — |
| LiveBench | — | 54.5% |
Math Too close to call
Command A: 33.5 (#172), DeepSeek-R1-Distill-Llama-70B: 34.3 (#161)
| Benchmark | Command A | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 51.4% |
| LiveBench Math | — | 58.1% |
| LMArena Math | 1300 | — |
| MATH Level 5 | — | 89.9% |
Knowledge Command A leads
Command A: 36.5 (#157), DeepSeek-R1-Distill-Llama-70B: 30.7 (#216)
| Benchmark | Command A | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| GPQA Diamond | — | 55.7% |
| Vectara Hallucination Rate | 9.3% | — |
| LMArena Expert | 1295 | — |
Multilingual Not comparable
Command A: 45.5 (#166), DeepSeek-R1-Distill-Llama-70B: —
| Benchmark | Command A | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| LMArena Non-English | 1313 | — |
| LMArena Chinese | 1327 | — |
| LMArena French | 1352 | — |
| LMArena German | 1341 | — |
| LMArena Japanese | 1283 | — |
| LMArena Korean | 1285 | — |
| LMArena Russian | 1314 | — |
| LMArena Spanish | 1346 | — |
Instruction Following Too close to call
Command A: 69.3 (#172), DeepSeek-R1-Distill-Llama-70B: 68.3 (#185)
| Benchmark | Command A | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| LiveBench Instruction Following | — | 69.9% |
| LMArena Instruction Following | 1309 | — |
Long Context Not comparable
Command A: 40.6 (#147), DeepSeek-R1-Distill-Llama-70B: —
| Benchmark | Command A | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| LMArena Longer Query | 1334 | — |
Writing & Preference DeepSeek-R1-Distill-Llama-70B leads
Command A: 47.8 (#204), DeepSeek-R1-Distill-Llama-70B: 49.0 (#189)
| Benchmark | Command A | DeepSeek-R1-Distill-Llama-70B |
|---|---|---|
| LMArena Text | 1331 | — |
| LMArena Creative Writing | 1319 | — |
| EQ-Bench Creative Writing | 1145 | — |
| LMArena Multi-Turn | 1338 | — |
| LiveBench Language | — | 23.8% |
Frequently asked questions
Is Command A better than DeepSeek-R1-Distill-Llama-70B?
DeepSeek-R1-Distill-Llama-70B is the stronger model overall, scoring 37.4 to 35.9 on the Noometry Index.
Is Command A or DeepSeek-R1-Distill-Llama-70B better for coding?
DeepSeek-R1-Distill-Llama-70B scores higher on coding benchmarks: 36.3 versus 26.8 in the Noometry coding category.
How many benchmarks do Command A and DeepSeek-R1-Distill-Llama-70B share?
1 benchmark has published results for both models. Command A has 24 scored results on Noometry and DeepSeek-R1-Distill-Llama-70B has 13.