Model comparison
Command A vs Deepseek Coder v2
Command A and Deepseek Coder v2 score almost the same on the Noometry Index (36.5 vs 35.9), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
Cohere
DeepSeekSummary
- They share 17 benchmarks with published results for both. Command A scores higher in 6 categories and Deepseek Coder v2 in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Deepseek Coder v2 leads 38.1 to 27.2.
Side by side
| Command A | Deepseek Coder v2 | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 36.5 | 35.9 |
| Released | 2025-03-13 | 2024-06-17 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Command A: 27.2 (#322), Deepseek Coder v2: 38.1 (#183)
| Benchmark | Command A | Deepseek Coder v2 |
|---|---|---|
| LMArena Coding | 1330 | 1251 |
| Aider Polyglot | 12% | — |
| BigCodeBench Instruct | — | 48.2% |
| BigCodeBench Complete | — | 59.7% |
| HumanEval+ | — | 82.3% |
| MBPP+ | — | 75.1% |
Agentic & Tool Use Not comparable
Command A: 35.9 (#40), Deepseek Coder v2: —
| Benchmark | Command A | Deepseek Coder v2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
Reasoning Deepseek Coder v2 leads
Command A: 18.3 (#283), Deepseek Coder v2: 23.6 (#176)
| Benchmark | Command A | Deepseek Coder v2 |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1207 |
| Kagi LLM Benchmark | 28.8% | — |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
| WinoGrande | — | 83.7% |
Math Command A leads
Command A: 36.2 (#171), Deepseek Coder v2: 34.9 (#190)
| Benchmark | Command A | Deepseek Coder v2 |
|---|---|---|
| LMArena Math | 1300 | 1241 |
| GSM8K | — | 94.5% |
Knowledge Command A leads
Command A: 37.1 (#159), Deepseek Coder v2: 32.3 (#212)
| Benchmark | Command A | Deepseek Coder v2 |
|---|---|---|
| LMArena Expert | 1295 | 1181 |
| Vectara Hallucination Rate | 9.3% | — |
| ARC (AI2) Challenge | — | 64.3% |
Multilingual Command A leads
Command A: 45.3 (#170), Deepseek Coder v2: 36.3 (#240)
| Benchmark | Command A | Deepseek Coder v2 |
|---|---|---|
| LMArena Non-English | 1313 | 1182 |
| LMArena Chinese | 1327 | 1201 |
| LMArena French | 1351 | 1185 |
| LMArena German | 1341 | 1164 |
| LMArena Japanese | 1285 | 1126 |
| LMArena Korean | 1285 | 1104 |
| LMArena Russian | 1314 | 1188 |
| LMArena Spanish | 1347 | 1153 |
Instruction Following Command A leads
Command A: 69.1 (#177), Deepseek Coder v2: 61.7 (#242)
| Benchmark | Command A | Deepseek Coder v2 |
|---|---|---|
| LMArena Instruction Following | 1309 | 1180 |
Long Context Command A leads
Command A: 40.6 (#151), Deepseek Coder v2: 37.0 (#224)
| Benchmark | Command A | Deepseek Coder v2 |
|---|---|---|
| LMArena Longer Query | 1334 | 1219 |
Writing & Preference Command A leads
Command A: 47.6 (#208), Deepseek Coder v2: 38.2 (#253)
| Benchmark | Command A | Deepseek Coder v2 |
|---|---|---|
| LMArena Text | 1331 | 1191 |
| LMArena Creative Writing | 1319 | 1120 |
| LMArena Multi-Turn | 1339 | 1177 |
| EQ-Bench Creative Writing | 1145 | — |
Frequently asked questions
Is Command A better than Deepseek Coder v2?
Command A and Deepseek Coder v2 score almost the same on the Noometry Index (36.5 vs 35.9), so choose on price, context window or the category you care about most.
Is Command A or Deepseek Coder v2 better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 27.2 in the Noometry coding category.
How many benchmarks do Command A and Deepseek Coder v2 share?
17 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Deepseek Coder v2 has 24.