Model comparison
Command R+ vs Qwen2.5 72B Instruct
Command R+ and Qwen2.5 72B Instruct score almost the same on the Noometry Index (32.4 vs 31.9), so choose on price, context window or the category you care about most.
Last verified . 23 shared benchmarks.
Cohere
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Command R+ scores higher in 2 categories and Qwen2.5 72B Instruct in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen2.5 72B Instruct leads 22.3 to 9.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 41.9% for Command R+ and 55.9% for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 per million input/output tokens, against $2.50 / $10 for Command R+.
- Qwen2.5 72B Instruct accepts more context: 131K tokens versus 128K.
Side by side
| Command R+ | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Cohere | Alibaba (Qwen) |
| Noometry Index | 32.4 | 31.9 |
| Released | 2024-08-30 | 2024-09 |
| Weights | Open | Open |
| Context window | 128K | 131K |
| Max output | 4K | 8K |
| Input $ / M tokens | $2.50 | $1.40 |
| Output $ / M tokens | $10 | $5.60 |
| Results tracked | 34 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 72B Instruct leads
Command R+: 29.1 (#309), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Command R+ | Qwen2.5 72B Instruct |
|---|---|---|
| BigCodeBench Instruct | 33.8% | 45.8% |
| LMArena Coding | 1187 | 1292 |
| BigCodeBench Complete | 41.9% | 55.9% |
| WeirdML | — | 16% |
| LiveBench Coding | 19.1% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Agentic & Tool Use Not comparable
Command R+: —, Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Command R+ | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
Command R+: 9.2 (#344), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Command R+ | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1271 |
| DTBench | 54.9% | 62.9% |
| LMCA | 5% | 13.4% |
| Epoch Capabilities Index | 119.34 | 129 |
| SimpleBench | 17.4% | — |
| LiveBench Reasoning | 24.8% | — |
| LiveBench Data Analysis | 38.1% | — |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| LiveBench | 31.8% | — |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Command R+ leads
Command R+: 28.9 (#242), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Command R+ | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1188 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| LiveBench Math | 21.3% | — |
| MATH Level 5 | — | 63.2% |
Knowledge Command R+ leads
Command R+: 36.4 (#169), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Command R+ | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1174 | 1245 |
| MMLU | 69.4% | 85.3% |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| Vectara Hallucination Rate | 6.9% | — |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| TriviaQA | — | 71.9% |
Multilingual Qwen2.5 72B Instruct leads
Command R+: 38.6 (#227), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Command R+ | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1216 | 1252 |
| LMArena Chinese | 1226 | 1272 |
| LMArena French | 1209 | 1280 |
| LMArena German | 1216 | 1234 |
| LMArena Japanese | 1166 | 1180 |
| LMArena Korean | 1138 | 1188 |
| LMArena Russian | 1227 | 1264 |
| LMArena Spanish | 1189 | 1256 |
Instruction Following Qwen2.5 72B Instruct leads
Command R+: 60.0 (#254), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Command R+ | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1197 | 1254 |
| LiveBench Instruction Following | 57.6% | — |
| IFEval | — | 80.6% |
Long Context Qwen2.5 72B Instruct leads
Command R+: 37.3 (#219), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Command R+ | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1230 | 1282 |
Writing & Preference Qwen2.5 72B Instruct leads
Command R+: 43.5 (#228), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Command R+ | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1229 | 1269 |
| LMArena Creative Writing | 1235 | 1221 |
| LMArena Multi-Turn | 1213 | 1272 |
| WildBench | — | 80.2% |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Qwen2.5 72B Instruct?
Command R+ and Qwen2.5 72B Instruct score almost the same on the Noometry Index (32.4 vs 31.9), so choose on price, context window or the category you care about most.
Which is cheaper, Command R+ or Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct is cheaper. It lists at $1.40 per million input tokens and $5.60 per million output tokens; Command R+ lists at $2.50 and $10.
Is Command R+ or Qwen2.5 72B Instruct better for coding?
Qwen2.5 72B Instruct scores higher on coding benchmarks: 33.2 versus 29.1 in the Noometry coding category.
Which has the bigger context window?
Qwen2.5 72B Instruct does, with 131K tokens against 128K.
How many benchmarks do Command R+ and Qwen2.5 72B Instruct share?
23 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Qwen2.5 72B Instruct has 43.