Model comparison
Command A vs Qwen2-72B
Command A is the stronger model overall, scoring 35.9 to 29.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Cohere
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Command A scores higher in 7 categories and Qwen2-72B in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Command A leads 35.7 to 16.9.
Side by side
| Command A | Qwen2-72B | |
|---|---|---|
| Provider | Cohere | Alibaba (Qwen) |
| Noometry Index | 35.9 | 29.5 |
| Released | 2025-03-13 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 24 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2-72B leads
Command A: 26.8 (#317), Qwen2-72B: 28.7 (#303)
| Benchmark | Command A | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1331 | 1196 |
| Aider Polyglot | 12% | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Command A leads
Command A: 35.7 (#36), Qwen2-72B: 16.9 (#138)
| Benchmark | Command A | Qwen2-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Command A: 17.7 (#276), Qwen2-72B: 22.2 (#184)
| Benchmark | Command A | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1191 |
| Kagi LLM Benchmark | 28.8% | — |
| DTBench | 61.3% | — |
| LMCA | 10.3% | — |
| Epoch Capabilities Index | — | 125.27 |
Math Command A leads
Command A: 33.5 (#172), Qwen2-72B: 27.9 (#232)
| Benchmark | Command A | Qwen2-72B |
|---|---|---|
| LMArena Math | 1300 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Command A leads
Command A: 36.5 (#157), Qwen2-72B: 21.2 (#270)
| Benchmark | Command A | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1295 | 1171 |
| GPQA Diamond | — | 40.8% |
| Vectara Hallucination Rate | 9.3% | — |
| MMLU | — | 82.4% |
Multilingual Command A leads
Command A: 45.5 (#166), Qwen2-72B: 36.0 (#239)
| Benchmark | Command A | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1313 | 1176 |
| LMArena Chinese | 1327 | 1240 |
| LMArena French | 1352 | 1169 |
| LMArena German | 1341 | 1151 |
| LMArena Japanese | 1283 | 1111 |
| LMArena Korean | 1285 | 1083 |
| LMArena Russian | 1314 | 1169 |
| LMArena Spanish | 1346 | 1168 |
Instruction Following Command A leads
Command A: 69.3 (#172), Qwen2-72B: 62.0 (#236)
| Benchmark | Command A | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1309 | 1181 |
Long Context Command A leads
Command A: 40.6 (#147), Qwen2-72B: 36.1 (#230)
| Benchmark | Command A | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1334 | 1193 |
Writing & Preference Command A leads
Command A: 47.8 (#204), Qwen2-72B: 41.0 (#236)
| Benchmark | Command A | Qwen2-72B |
|---|---|---|
| LMArena Text | 1331 | 1203 |
| LMArena Creative Writing | 1319 | 1181 |
| LMArena Multi-Turn | 1338 | 1195 |
| EQ-Bench Creative Writing | 1145 | — |
Frequently asked questions
Is Command A better than Qwen2-72B?
Command A is the stronger model overall, scoring 35.9 to 29.5 on the Noometry Index.
Is Command A or Qwen2-72B better for coding?
Qwen2-72B scores higher on coding benchmarks: 28.7 versus 26.8 in the Noometry coding category.
How many benchmarks do Command A and Qwen2-72B share?
17 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Qwen2-72B has 26.