Model comparison
Command R vs Qwen1.5-32B
Command R is the stronger model overall, scoring 31.0 to 30.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
Cohere
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Command R scores higher in 5 categories and Qwen1.5-32B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command R leads 30.5 to 13.5.
Side by side
| Command R | Qwen1.5-32B | |
|---|---|---|
| Provider | Cohere | Alibaba (Qwen) |
| Noometry Index | 31.0 | 30.0 |
| Released | 2024-08-30 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-32B leads
Command R: 28.8 (#301), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Command R | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 37.1% | 32.3% |
| LMArena Coding | 1170 | 1155 |
| BigCodeBench Complete | 45.2% | 42% |
| LiveBench Coding | 17.9% | — |
Reasoning Qwen1.5-32B leads
Command R: 13.3 (#329), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Command R | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1131 |
| LiveBench Reasoning | 21.9% | — |
| DTBench | 46.4% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| LiveBench | 27.5% | — |
Math Qwen1.5-32B leads
Command R: 25.8 (#244), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Command R | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1155 | 1155 |
| LiveBench Math | 19.4% | — |
Knowledge Command R leads
Command R: 30.5 (#219), Qwen1.5-32B: 13.5 (#291)
| Benchmark | Command R | Qwen1.5-32B |
|---|---|---|
| LMArena Expert | 1138 | 1126 |
| MMLU | 65.2% | 74.4% |
| GPQA Diamond | — | 30.7% |
Multilingual Command R leads
Command R: 35.9 (#240), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Command R | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1174 | 1106 |
| LMArena Chinese | 1182 | 1176 |
| LMArena French | 1161 | 1100 |
| LMArena German | 1176 | 1058 |
| LMArena Japanese | 1143 | 1027 |
| LMArena Korean | 1162 | 1007 |
| LMArena Russian | 1174 | 1073 |
| LMArena Spanish | 1150 | 1089 |
Instruction Following Too close to call
Command R: 58.3 (#256), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Command R | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1167 | 1116 |
| LiveBench Instruction Following | 55.6% | — |
Long Context Command R leads
Command R: 36.3 (#226), Qwen1.5-32B: 34.7 (#241)
| Benchmark | Command R | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1198 | 1146 |
Writing & Preference Command R leads
Command R: 38.4 (#248), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Command R | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1187 | 1137 |
| LMArena Creative Writing | 1170 | 1083 |
| LMArena Multi-Turn | 1163 | 1140 |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than Qwen1.5-32B?
Command R is the stronger model overall, scoring 31.0 to 30.0 on the Noometry Index.
Is Command R or Qwen1.5-32B better for coding?
Qwen1.5-32B scores higher on coding benchmarks: 31.1 versus 28.8 in the Noometry coding category.
How many benchmarks do Command R and Qwen1.5-32B share?
20 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Qwen1.5-32B has 21.