Model comparison
Command R+ vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 32.0 on the Noometry Index.
Last verified . 22 shared benchmarks.
Cohere
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Command R+ scores higher in 0 categories and Qwen3 235B-A22B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 48.5 to 26.6.
- The biggest single-benchmark swing is DTBench: 54.9% for Command R+ and 80.3% 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 R+.
- Qwen3 235B-A22B accepts more context: 131K tokens versus 128K.
Side by side
| Command R+ | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Cohere | Alibaba (Qwen) |
| Noometry Index | 32.0 | 43.2 |
| Released | 2024-08-30 | 2025-04 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 16K |
| Input $ / M tokens | $2.50 | $0.70 |
| Output $ / M tokens | $10 | $2.80 |
| Results tracked | 34 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Command R+: 28.6 (#304), Qwen3 235B-A22B: 43.8 (#72)
| Benchmark | Command R+ | Qwen3 235B-A22B |
|---|---|---|
| LMArena Coding | 1187 | 1445 |
| Aider Polyglot | — | 59.6% |
| SciCode | — | 42.4% |
| WeirdML | — | 41% |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, Qwen3 235B-A22B: 33.7 (#48)
| Benchmark | Command R+ | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Vending-Bench 2 | — | -11.34 |
Reasoning Qwen3 235B-A22B leads
Command R+: 8.9 (#341), Qwen3 235B-A22B: 15.8 (#302)
| Benchmark | Command R+ | Qwen3 235B-A22B |
|---|---|---|
| SimpleBench | 17.4% | 31% |
| LMArena Hard Prompts | 1186 | 1433 |
| DTBench | 54.9% | 80.3% |
| LMCA | 5% | 29.3% |
| Epoch Capabilities Index | 119.28 | 143.87 |
| ARC-AGI-2 | — | 1.3% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| LiveBench Reasoning | 24.8% | — |
| Mystery Game Puzzles | — | 9% |
| LiveBench Data Analysis | 38.1% | — |
| ForecastBench | — | 59.7 |
| LiveBench | 31.8% | — |
Math Qwen3 235B-A22B leads
Command R+: 26.6 (#239), Qwen3 235B-A22B: 48.5 (#51)
| Benchmark | Command R+ | Qwen3 235B-A22B |
|---|---|---|
| LMArena Math | 1188 | 1431 |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| Omni-MATH | — | 71.8% |
| LiveBench Math | 21.3% | — |
| MATH Level 5 | — | 68.9% |
| FrontierMath (Feb 2025 set) | — | 8.5% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Command R+: 35.9 (#165), Qwen3 235B-A22B: 49.5 (#67)
| Benchmark | Command R+ | Qwen3 235B-A22B |
|---|---|---|
| Vectara Hallucination Rate | 6.9% | 9.3% |
| LMArena Expert | 1174 | 1460 |
| GPQA Diamond | — | 80.1% |
| SimpleQA Verified | — | 40.4% |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| GPQA (HELM) | — | 72.7% |
| MMLU | 69.4% | — |
Multilingual Qwen3 235B-A22B leads
Command R+: 38.8 (#222), Qwen3 235B-A22B: 52.5 (#84)
| Benchmark | Command R+ | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1216 | 1410 |
| LMArena Chinese | 1226 | 1481 |
| LMArena French | 1208 | 1445 |
| LMArena German | 1216 | 1432 |
| LMArena Japanese | 1166 | 1400 |
| LMArena Korean | 1138 | 1391 |
| LMArena Russian | 1227 | 1411 |
| LMArena Spanish | 1189 | 1429 |
Instruction Following Qwen3 235B-A22B leads
Command R+: 60.2 (#249), Qwen3 235B-A22B: 72.8 (#132)
| Benchmark | Command R+ | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1197 | 1408 |
| LiveBench Instruction Following | 57.6% | — |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
Command R+: 37.3 (#214), Qwen3 235B-A22B: 46.1 (#25)
| Benchmark | Command R+ | Qwen3 235B-A22B |
|---|---|---|
| LMArena Longer Query | 1231 | 1426 |
| Fiction.LiveBench | — | 75% |
Writing & Preference Qwen3 235B-A22B leads
Command R+: 43.7 (#223), Qwen3 235B-A22B: 59.8 (#103)
| Benchmark | Command R+ | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1229 | 1419 |
| LMArena Creative Writing | 1235 | 1384 |
| LMArena Multi-Turn | 1213 | 1432 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1366 |
| WildBench | — | 86.6% |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.2 to 32.0 on the Noometry Index.
Which is cheaper, Command R+ 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 R+ lists at $2.50 and $10.
Is Command R+ or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 43.8 versus 28.6 in the Noometry coding category.
Which has the bigger context window?
Qwen3 235B-A22B does, with 131K tokens against 128K.
How many benchmarks do Command R+ and Qwen3 235B-A22B share?
22 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Qwen3 235B-A22B has 49.