Model comparison
Command R+ vs Qwen1.5-110B
Qwen1.5-110B is the stronger model overall, scoring 33.6 to 32.0 on the Noometry Index.
Last verified . 19 shared benchmarks.
Cohere
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Command R+ scores higher in 4 categories and Qwen1.5-110B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen1.5-110B leads 21.7 to 8.9.
Side by side
| Command R+ | Qwen1.5-110B | |
|---|---|---|
| Provider | Cohere | Alibaba (Qwen) |
| Noometry Index | 32.0 | 33.6 |
| Released | 2024-08-30 | 2024-04-25 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $2.50 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 34 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-110B leads
Command R+: 28.6 (#304), Qwen1.5-110B: 32.4 (#260)
| Benchmark | Command R+ | Qwen1.5-110B |
|---|---|---|
| BigCodeBench Instruct | 33.8% | 35% |
| LMArena Coding | 1187 | 1184 |
| BigCodeBench Complete | 41.9% | 44.4% |
| LiveBench Coding | 19.1% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 63.5% | — |
Reasoning Qwen1.5-110B leads
Command R+: 8.9 (#341), Qwen1.5-110B: 21.7 (#192)
| Benchmark | Command R+ | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1186 | 1168 |
| SimpleBench | 17.4% | — |
| LiveBench Reasoning | 24.8% | — |
| DTBench | 54.9% | — |
| LiveBench Data Analysis | 38.1% | — |
| LMCA | 5% | — |
| Epoch Capabilities Index | 119.28 | — |
| ForecastBench | — | 57.7 |
| LiveBench | 31.8% | — |
Math Qwen1.5-110B leads
Command R+: 26.6 (#239), Qwen1.5-110B: 31.1 (#199)
| Benchmark | Command R+ | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1188 | 1185 |
| LiveBench Math | 21.3% | — |
Knowledge Command R+ leads
Command R+: 35.9 (#165), Qwen1.5-110B: 30.7 (#217)
| Benchmark | Command R+ | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1174 | 1144 |
| Vectara Hallucination Rate | 6.9% | — |
| MMLU | 69.4% | — |
Multilingual Command R+ leads
Command R+: 38.8 (#222), Qwen1.5-110B: 33.8 (#245)
| Benchmark | Command R+ | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1216 | 1142 |
| LMArena Chinese | 1226 | 1206 |
| LMArena French | 1208 | 1150 |
| LMArena German | 1216 | 1123 |
| LMArena Japanese | 1166 | 1074 |
| LMArena Korean | 1138 | 1044 |
| LMArena Russian | 1227 | 1118 |
| LMArena Spanish | 1189 | 1141 |
Instruction Following Too close to call
Command R+: 60.2 (#249), Qwen1.5-110B: 60.6 (#247)
| Benchmark | Command R+ | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1197 | 1158 |
| LiveBench Instruction Following | 57.6% | — |
Long Context Command R+ leads
Command R+: 37.3 (#214), Qwen1.5-110B: 35.0 (#237)
| Benchmark | Command R+ | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1231 | 1157 |
Writing & Preference Command R+ leads
Command R+: 43.7 (#223), Qwen1.5-110B: 38.1 (#250)
| Benchmark | Command R+ | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1229 | 1175 |
| LMArena Creative Writing | 1235 | 1148 |
| LMArena Multi-Turn | 1213 | 1160 |
| LiveBench Language | 29.7% | — |
Frequently asked questions
Is Command R+ better than Qwen1.5-110B?
Qwen1.5-110B is the stronger model overall, scoring 33.6 to 32.0 on the Noometry Index.
Is Command R+ or Qwen1.5-110B better for coding?
Qwen1.5-110B scores higher on coding benchmarks: 32.4 versus 28.6 in the Noometry coding category.
How many benchmarks do Command R+ and Qwen1.5-110B share?
19 benchmarks have published results for both models. Command R+ has 34 scored results on Noometry and Qwen1.5-110B has 20.