Model comparison
Command R+ vs Qwen-14B
Command R+ is the stronger model overall, scoring 32.4 to 31.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Cohere
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Command R+ scores higher in 4 categories and Qwen-14B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Command R+ leads 43.5 to 27.6.
Side by side
| Command R+ | Qwen-14B | |
|---|---|---|
| Provider | Cohere | Alibaba (Qwen) |
| Noometry Index | 32.4 | 31.4 |
| Released | 2024-08-30 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 34 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen-14B leads
Command R+: 29.1 (#309), Qwen-14B: 31.2 (#288)
| Benchmark | Command R+ | Qwen-14B |
|---|---|---|
| LMArena Coding | 1187 | 1071 |
| BigCodeBench Instruct | 33.8% | — |
| LiveBench Coding | 19.1% | — |
| BigCodeBench Complete | 41.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Reasoning Qwen-14B leads
Command R+: 9.2 (#344), Qwen-14B: 19.6 (#257)
| Benchmark | Command R+ | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1027 |
| Epoch Capabilities Index | 119.34 | 113.03 |
| SimpleBench | 17.4% | — |
| LiveBench Reasoning | 24.8% | — |
| DTBench | 54.9% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| LiveBench | 31.8% | — |
| PIQA | — | 79.9% |
Math Qwen-14B leads
Command R+: 28.9 (#242), Qwen-14B: 31.2 (#227)
| Benchmark | Command R+ | Qwen-14B |
|---|---|---|
| LMArena Math | 1188 | 1068 |
| LiveBench Math | 21.3% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Command R+: 36.4 (#169), Qwen-14B: —
| Benchmark | Command R+ | Qwen-14B |
|---|---|---|
| MMLU | 69.4% | 66.3% |
| Vectara Hallucination Rate | 6.9% | — |
| LMArena Expert | 1174 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
Multilingual Command R+ leads
Command R+: 38.6 (#227), Qwen-14B: 27.5 (#275)
| Benchmark | Command R+ | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1216 | 1041 |
| LMArena Chinese | 1226 | 1077 |
| LMArena French | 1209 | — |
| LMArena German | 1216 | — |
| LMArena Japanese | 1166 | — |
| LMArena Korean | 1138 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1189 | — |
Instruction Following Command R+ leads
Command R+: 60.0 (#254), Qwen-14B: 52.4 (#289)
| Benchmark | Command R+ | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1197 | 1031 |
| LiveBench Instruction Following | 57.6% | — |
Long Context Command R+ leads
Command R+: 37.3 (#219), Qwen-14B: 31.3 (#280)
| Benchmark | Command R+ | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1230 | 1028 |
Writing & Preference Command R+ leads
Command R+: 43.5 (#228), Qwen-14B: 27.6 (#299)
| Benchmark | Command R+ | Qwen-14B |
|---|---|---|
| LMArena Text | 1229 | 1051 |
| LMArena Creative Writing | 1235 | 1028 |
| LMArena Multi-Turn | 1213 | 1022 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Qwen-14B?
Command R+ is the stronger model overall, scoring 32.4 to 31.4 on the Noometry Index.
Is Command R+ or Qwen-14B better for coding?
Qwen-14B scores higher on coding benchmarks: 31.2 versus 29.1 in the Noometry coding category.
How many benchmarks do Command R+ and Qwen-14B share?
12 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Qwen-14B has 18.