Model comparison
Command A vs Qwen2.5 72B Instruct
Command A is the stronger model overall, scoring 36.5 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 1.8× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Cohere
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Command A scores higher in 7 categories and Qwen2.5 72B Instruct in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Command A leads 36.2 to 19.3.
- Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 per million input/output tokens, against $2.50 / $10 for Command A.
- Command A accepts more context: 256K tokens versus 131K.
Side by side
| Command A | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Cohere | Alibaba (Qwen) |
| Noometry Index | 36.5 | 31.9 |
| Released | 2025-03-13 | 2024-09 |
| Weights | Open | Open |
| Context window | 256K | 131K |
| Max output | 8K | 8K |
| Input $ / M tokens | $2.50 | $1.40 |
| Output $ / M tokens | $10 | $5.60 |
| Results tracked | 24 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 72B Instruct leads
Command A: 27.2 (#322), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Command A | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1330 | 1292 |
| Aider Polyglot | 12% | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Command A | Qwen2.5 72B Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | — |
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
Command A: 18.3 (#283), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Command A | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1326 | 1271 |
| DTBench | 61.3% | 62.9% |
| LMCA | 10.3% | 13.4% |
| Kagi LLM Benchmark | 28.8% | — |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Command A leads
Command A: 36.2 (#171), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Command A | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1300 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
Knowledge Command A leads
Command A: 37.1 (#159), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Command A | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1295 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual Command A leads
Command A: 45.3 (#170), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Command A | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1313 | 1252 |
| LMArena Chinese | 1327 | 1272 |
| LMArena French | 1351 | 1280 |
| LMArena German | 1341 | 1234 |
| LMArena Japanese | 1285 | 1180 |
| LMArena Korean | 1285 | 1188 |
| LMArena Russian | 1314 | 1264 |
| LMArena Spanish | 1347 | 1256 |
Instruction Following Command A leads
Command A: 69.1 (#177), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Command A | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1309 | 1254 |
| IFEval | — | 80.6% |
Long Context Command A leads
Command A: 40.6 (#151), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Command A | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1334 | 1282 |
Writing & Preference Too close to call
Command A: 47.6 (#208), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Command A | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1331 | 1269 |
| LMArena Creative Writing | 1319 | 1221 |
| LMArena Multi-Turn | 1339 | 1272 |
| EQ-Bench Creative Writing | 1145 | — |
| WildBench | — | 80.2% |
Frequently asked questions
Is Command A better than Qwen2.5 72B Instruct?
Command A is the stronger model overall, scoring 36.5 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 1.8× less per token, which makes it the better buy when Command A's lead doesn't matter for your workload.
Which is cheaper, Command A or Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct is cheaper. It lists at $1.40 per million input tokens and $5.60 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or Qwen2.5 72B Instruct better for coding?
Qwen2.5 72B Instruct scores higher on coding benchmarks: 33.2 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
Command A does, with 256K tokens against 131K.
How many benchmarks do Command A and Qwen2.5 72B Instruct share?
19 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Qwen2.5 72B Instruct has 43.