Model comparison
Command A vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 36.5 on the Noometry Index.
Last verified . 21 shared benchmarks.
Cohere
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Command A scores higher in 1 category and Qwen3.5 397B-A17B in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 397B-A17B leads 53.3 to 37.1.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 28.8% for Command A and 73.7% for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B is cheaper at $0.60 / $3.60 per million input/output tokens, against $2.50 / $10 for Command A.
- Qwen3.5 397B-A17B accepts more context: 262K tokens versus 256K.
Side by side
| Command A | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | Cohere | Alibaba (Qwen) |
| Noometry Index | 36.5 | 46.0 |
| Released | 2025-03-13 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 256K | 262K |
| Max output | 8K | 66K |
| Input $ / M tokens | $2.50 | $0.60 |
| Output $ / M tokens | $10 | $3.60 |
| Results tracked | 24 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
Command A: 27.2 (#322), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | Command A | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Coding | 1330 | 1465 |
| Aider Polyglot | 12% | — |
| LMArena WebDev | — | 1400 |
Agentic & Tool Use Command A leads
Command A: 35.9 (#40), Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | Command A | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| Berkeley Function Calling Leaderboard | 57.1% | — |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
Reasoning Qwen3.5 397B-A17B leads
Command A: 18.3 (#283), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | Command A | Qwen3.5 397B-A17B |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 73.7% |
| LMArena Hard Prompts | 1326 | 1448 |
| DTBench | 61.3% | 87.5% |
| LMCA | 10.3% | 37.9% |
| NYT Connections (extended) | — | 58.9% |
| Chess Puzzles | — | 13% |
| Thematic Generalization | — | 65.1% |
| Mystery Game Puzzles | — | 18% |
| Epoch Capabilities Index | — | 146.65 |
Math Qwen3.5 397B-A17B leads
Command A: 36.2 (#171), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | Command A | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Math | 1300 | 1454 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
Knowledge Qwen3.5 397B-A17B leads
Command A: 37.1 (#159), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | Command A | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Expert | 1295 | 1462 |
| GPQA Diamond | — | 86.4% |
| Vectara Hallucination Rate | 9.3% | — |
Multimodal Not comparable
Command A: —, Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | Command A | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |
Multilingual Qwen3.5 397B-A17B leads
Command A: 45.3 (#170), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | Command A | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1313 | 1430 |
| LMArena Chinese | 1327 | 1500 |
| LMArena French | 1351 | 1461 |
| LMArena German | 1341 | 1447 |
| LMArena Japanese | 1285 | 1426 |
| LMArena Korean | 1285 | 1384 |
| LMArena Russian | 1314 | 1429 |
| LMArena Spanish | 1347 | 1441 |
Instruction Following Qwen3.5 397B-A17B leads
Command A: 69.1 (#177), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | Command A | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1309 | 1424 |
Long Context Qwen3.5 397B-A17B leads
Command A: 40.6 (#151), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | Command A | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1334 | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
Command A: 47.6 (#208), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | Command A | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1331 | 1438 |
| LMArena Creative Writing | 1319 | 1401 |
| EQ-Bench Creative Writing | 1145 | 1478 |
| LMArena Multi-Turn | 1339 | 1446 |
Frequently asked questions
Is Command A better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 36.5 on the Noometry Index.
Which is cheaper, Command A or Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is cheaper. It lists at $0.60 per million input tokens and $3.60 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or Qwen3.5 397B-A17B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 27.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 397B-A17B does, with 262K tokens against 256K.
How many benchmarks do Command A and Qwen3.5 397B-A17B share?
21 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Qwen3.5 397B-A17B has 36.