Model comparison
Command A vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 35.9 on the Noometry Index.
Last verified . 24 shared benchmarks.
Cohere
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. Command A scores higher in 2 categories and Qwen3 235B-A22B in 7 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen3 235B-A22B leads 43.8 to 26.8.
- The biggest single-benchmark swing is Aider Polyglot: 12% for Command A and 59.6% for Qwen3 235B-A22B.
- Qwen3 235B-A22B is cheaper at $0.70 / $2.80 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 | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Cohere | Alibaba (Qwen) |
| Noometry Index | 35.9 | 43.2 |
| Released | 2025-03-13 | 2025-04 |
| Weights | Open | Open |
| Context window | 256K | 131K |
| Max output | 8K | 16K |
| Input $ / M tokens | $2.50 | $0.70 |
| Output $ / M tokens | $10 | $2.80 |
| Results tracked | 24 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Command A: 26.8 (#317), Qwen3 235B-A22B: 43.8 (#72)
| Benchmark | Command A | Qwen3 235B-A22B |
|---|---|---|
| Aider Polyglot | 12% | 59.6% |
| LMArena Coding | 1331 | 1445 |
| SciCode | — | 42.4% |
| WeirdML | — | 41% |
Agentic & Tool Use Command A leads
Command A: 35.7 (#36), Qwen3 235B-A22B: 33.7 (#48)
| Benchmark | Command A | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 57.1% | 52.1% |
| Vending-Bench 2 | — | -11.34 |
Reasoning Command A leads
Command A: 17.7 (#276), Qwen3 235B-A22B: 15.8 (#302)
| Benchmark | Command A | Qwen3 235B-A22B |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 69.4% |
| LMArena Hard Prompts | 1326 | 1433 |
| DTBench | 61.3% | 80.3% |
| LMCA | 10.3% | 29.3% |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 9% |
| Epoch Capabilities Index | — | 143.87 |
| ForecastBench | — | 59.7 |
Math Qwen3 235B-A22B leads
Command A: 33.5 (#172), Qwen3 235B-A22B: 48.5 (#51)
| Benchmark | Command A | Qwen3 235B-A22B |
|---|---|---|
| LMArena Math | 1300 | 1431 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| Omni-MATH | — | 71.8% |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Command A: 36.5 (#157), Qwen3 235B-A22B: 49.5 (#67)
| Benchmark | Command A | Qwen3 235B-A22B |
|---|---|---|
| Vectara Hallucination Rate | 9.3% | 9.3% |
| LMArena Expert | 1295 | 1460 |
| GPQA Diamond | — | 80.1% |
| SimpleQA Verified | — | 40.4% |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| GPQA (HELM) | — | 72.7% |
Multilingual Qwen3 235B-A22B leads
Command A: 45.5 (#166), Qwen3 235B-A22B: 52.5 (#84)
| Benchmark | Command A | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1313 | 1410 |
| LMArena Chinese | 1327 | 1481 |
| LMArena French | 1352 | 1445 |
| LMArena German | 1341 | 1432 |
| LMArena Japanese | 1283 | 1400 |
| LMArena Korean | 1285 | 1391 |
| LMArena Russian | 1314 | 1411 |
| LMArena Spanish | 1346 | 1429 |
Instruction Following Qwen3 235B-A22B leads
Command A: 69.3 (#172), Qwen3 235B-A22B: 72.8 (#132)
| Benchmark | Command A | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1309 | 1408 |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
Command A: 40.6 (#147), Qwen3 235B-A22B: 46.1 (#25)
| Benchmark | Command A | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1334 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Qwen3 235B-A22B leads
Command A: 47.8 (#204), Qwen3 235B-A22B: 59.8 (#103)
| Benchmark | Command A | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1331 | 1419 |
| LMArena Creative Writing | 1319 | 1384 |
| EQ-Bench Creative Writing | 1145 | 1366 |
| LMArena Multi-Turn | 1338 | 1432 |
| Short-Story Creative Writing | — | 83% |
| WildBench | — | 86.6% |
Frequently asked questions
Is Command A better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 35.9 on the Noometry Index.
Which is cheaper, Command A or Qwen3 235B-A22B?
Qwen3 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Command A lists at $2.50 and $10.
Is Command A or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 43.8 versus 26.8 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 Qwen3 235B-A22B share?
24 benchmarks have published results for both models. Command A has 24 scored results on Noometry and Qwen3 235B-A22B has 49.