Model comparison
Command A vs DeepSeek LLM 67B
Command A is the stronger model overall, scoring 36.5 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
Cohere
DeepSeekSummary
- They share 10 benchmarks with published results for both. Command A scores higher in 7 categories and DeepSeek LLM 67B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command A leads 37.1 to 7.0.
Side by side
| Command A | DeepSeek LLM 67B | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 36.5 | 24.9 |
| Released | 2025-03-13 | 2023-11-29 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek LLM 67B leads
Command A: 27.2 (#322), DeepSeek LLM 67B: 31.9 (#278)
| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| LMArena Coding | 1330 | 1096 |
| Aider Polyglot | 12% | — |
Agentic & Tool Use Not comparable
Command A: 35.9 (#40), DeepSeek LLM 67B: —
| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Command A leads
Command A: 18.3 (#283), DeepSeek LLM 67B: 16.5 (#304)
| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1070 |
| Kagi LLM Benchmark | 28.8% | — |
| Chess Puzzles | — | 0% |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
| Epoch Capabilities Index | — | 110.5 |
Math Command A leads
Command A: 36.2 (#171), DeepSeek LLM 67B: 8.7 (#324)
| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| LMArena Math | 1300 | 1108 |
| OTIS Mock AIME 2024-2025 | — | 0.8% |
| MATH Level 5 | — | 6.4% |
Knowledge Command A leads
Command A: 37.1 (#159), DeepSeek LLM 67B: 7.0 (#313)
| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| GPQA Diamond | — | 24.6% |
| Vectara Hallucination Rate | 9.3% | — |
| LMArena Expert | 1295 | — |
Multilingual Command A leads
Command A: 45.3 (#170), DeepSeek LLM 67B: 29.4 (#267)
| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| LMArena Non-English | 1313 | 1073 |
| LMArena Chinese | 1327 | 1132 |
| LMArena French | 1351 | — |
| LMArena German | 1341 | — |
| LMArena Japanese | 1285 | — |
| LMArena Korean | 1285 | — |
| LMArena Russian | 1314 | — |
| LMArena Spanish | 1347 | — |
Instruction Following Command A leads
Command A: 69.1 (#177), DeepSeek LLM 67B: 55.4 (#277)
| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| LMArena Instruction Following | 1309 | 1079 |
Long Context Command A leads
Command A: 40.6 (#151), DeepSeek LLM 67B: 33.1 (#265)
| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| LMArena Longer Query | 1334 | 1092 |
Writing & Preference Command A leads
Command A: 47.6 (#208), DeepSeek LLM 67B: 31.6 (#282)
| Benchmark | Command A | DeepSeek LLM 67B |
|---|---|---|
| LMArena Text | 1331 | 1105 |
| LMArena Creative Writing | 1319 | 1067 |
| LMArena Multi-Turn | 1339 | 1082 |
| EQ-Bench Creative Writing | 1145 | — |
Frequently asked questions
Is Command A better than DeepSeek LLM 67B?
Command A is the stronger model overall, scoring 36.5 to 24.9 on the Noometry Index.
Is Command A or DeepSeek LLM 67B better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 27.2 in the Noometry coding category.
How many benchmarks do Command A and DeepSeek LLM 67B share?
10 benchmarks have published results for both models. Command A has 24 scored results on Noometry and DeepSeek LLM 67B has 15.