Model comparison
Command R vs Qwen2-72B
Command R is the stronger model overall, scoring 31.0 to 29.5 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 3 categories and Qwen2-72B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Command R leads 30.5 to 21.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 45.2% for Command R and 54% for Qwen2-72B.
Side by side
| Command R | Qwen2-72B | |
|---|---|---|
| Provider | Cohere | Alibaba (Qwen) |
| Noometry Index | 31.0 | 29.5 |
| Released | 2024-08-30 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Command R: 28.8 (#301), Qwen2-72B: 28.7 (#303)
| Benchmark | Command R | Qwen2-72B |
|---|---|---|
| BigCodeBench Instruct | 37.1% | 38.5% |
| LMArena Coding | 1170 | 1196 |
| BigCodeBench Complete | 45.2% | 54% |
| WeirdML | — | 11.3% |
| LiveBench Coding | 17.9% | — |
Agentic & Tool Use Not comparable
Command R: —, Qwen2-72B: 16.9 (#138)
| Benchmark | Command R | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Command R: 13.3 (#329), Qwen2-72B: 22.2 (#184)
| Benchmark | Command R | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1191 |
| LiveBench Reasoning | 21.9% | — |
| DTBench | 46.4% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| Epoch Capabilities Index | — | 125.27 |
| LiveBench | 27.5% | — |
Math Qwen2-72B leads
Command R: 25.8 (#244), Qwen2-72B: 27.9 (#232)
| Benchmark | Command R | Qwen2-72B |
|---|---|---|
| LMArena Math | 1155 | 1235 |
| LiveBench Math | 19.4% | — |
| MATH Level 5 | — | 39.1% |
Knowledge Command R leads
Command R: 30.5 (#219), Qwen2-72B: 21.2 (#270)
| Benchmark | Command R | Qwen2-72B |
|---|---|---|
| LMArena Expert | 1138 | 1171 |
| MMLU | 65.2% | 82.4% |
| GPQA Diamond | — | 40.8% |
Multilingual Too close to call
Command R: 35.9 (#240), Qwen2-72B: 36.0 (#239)
| Benchmark | Command R | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1174 | 1176 |
| LMArena Chinese | 1182 | 1240 |
| LMArena French | 1161 | 1169 |
| LMArena German | 1176 | 1151 |
| LMArena Japanese | 1143 | 1111 |
| LMArena Korean | 1162 | 1083 |
| LMArena Russian | 1174 | 1169 |
| LMArena Spanish | 1150 | 1168 |
Instruction Following Qwen2-72B leads
Command R: 58.3 (#256), Qwen2-72B: 62.0 (#236)
| Benchmark | Command R | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1167 | 1181 |
| LiveBench Instruction Following | 55.6% | — |
Long Context Too close to call
Command R: 36.3 (#226), Qwen2-72B: 36.1 (#230)
| Benchmark | Command R | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1198 | 1193 |
Writing & Preference Qwen2-72B leads
Command R: 38.4 (#248), Qwen2-72B: 41.0 (#236)
| Benchmark | Command R | Qwen2-72B |
|---|---|---|
| LMArena Text | 1187 | 1203 |
| LMArena Creative Writing | 1170 | 1181 |
| LMArena Multi-Turn | 1163 | 1195 |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than Qwen2-72B?
Command R is the stronger model overall, scoring 31.0 to 29.5 on the Noometry Index.
Is Command R or Qwen2-72B better for coding?
They score almost the same on coding (28.8 vs 28.7); test both on your own repository before choosing.
How many benchmarks do Command R and Qwen2-72B share?
20 benchmarks have published results for both models. Command R has 29 scored results on Noometry and Qwen2-72B has 26.