Model comparison
Command R vs Qwen1.5-110B
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 31.4 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 3 categories and Qwen1.5-110B in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen1.5-110B leads 22.7 to 13.8.
Side by side
| Command R | Qwen1.5-110B | |
|---|---|---|
| Provider | Cohere | Alibaba (Qwen) |
| Noometry Index | 31.4 | 34.2 |
| Released | 2024-08-30 | 2024-04-25 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 29 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-110B leads
Command R: 29.3 (#306), Qwen1.5-110B: 33.0 (#264)
| Benchmark | Command R | Qwen1.5-110B |
|---|---|---|
| BigCodeBench Instruct | 37.1% | 35% |
| LMArena Coding | 1169 | 1184 |
| BigCodeBench Complete | 45.2% | 44.4% |
| LiveBench Coding | 17.9% | — |
Reasoning Qwen1.5-110B leads
Command R: 13.8 (#331), Qwen1.5-110B: 22.7 (#189)
| Benchmark | Command R | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1164 | 1168 |
| LiveBench Reasoning | 21.9% | — |
| DTBench | 46.4% | — |
| LiveBench Data Analysis | 33.3% | — |
| LMCA | 9.2% | — |
| ForecastBench | — | 57.7 |
| LiveBench | 27.5% | — |
Math Qwen1.5-110B leads
Command R: 28.0 (#246), Qwen1.5-110B: 33.7 (#201)
| Benchmark | Command R | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1155 | 1185 |
| LiveBench Math | 19.4% | — |
Knowledge Too close to call
Command R: 31.0 (#221), Qwen1.5-110B: 31.2 (#219)
| Benchmark | Command R | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1138 | 1144 |
| MMLU | 65.2% | — |
Multilingual Command R leads
Command R: 35.7 (#245), Qwen1.5-110B: 33.6 (#250)
| Benchmark | Command R | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1174 | 1142 |
| LMArena Chinese | 1182 | 1206 |
| LMArena French | 1162 | 1151 |
| LMArena German | 1176 | 1123 |
| LMArena Japanese | 1143 | 1074 |
| LMArena Korean | 1163 | 1044 |
| LMArena Russian | 1174 | 1118 |
| LMArena Spanish | 1151 | 1142 |
Instruction Following Qwen1.5-110B leads
Command R: 58.1 (#261), Qwen1.5-110B: 60.3 (#252)
| Benchmark | Command R | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1167 | 1158 |
| LiveBench Instruction Following | 55.6% | — |
Long Context Command R leads
Command R: 36.3 (#231), Qwen1.5-110B: 35.1 (#242)
| Benchmark | Command R | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1198 | 1157 |
Writing & Preference Too close to call
Command R: 38.2 (#254), Qwen1.5-110B: 38.0 (#255)
| Benchmark | Command R | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1187 | 1175 |
| LMArena Creative Writing | 1170 | 1148 |
| LMArena Multi-Turn | 1163 | 1160 |
| LiveBench Language | 16.7% | — |
Frequently asked questions
Is Command R better than Qwen1.5-110B?
Qwen1.5-110B is the stronger model overall, scoring 34.2 to 31.4 on the Noometry Index.
Is Command R or Qwen1.5-110B better for coding?
Qwen1.5-110B scores higher on coding benchmarks: 33.0 versus 29.3 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 29 scored results on Noometry and Qwen1.5-110B has 20.