Model comparison
C4ai Aya Expanse 32b vs Qwen1.5-72B
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 30.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
Cohere
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 8 categories and Qwen1.5-72B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where C4ai Aya Expanse 32b leads 33.2 to 11.5.
Side by side
| C4ai Aya Expanse 32b | Qwen1.5-72B | |
|---|---|---|
| Provider | Cohere | Alibaba (Qwen) |
| Noometry Index | 35.9 | 30.8 |
| Released | 2024-10-24 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 34.8 (#231), Qwen1.5-72B: 31.9 (#277)
| Benchmark | C4ai Aya Expanse 32b | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1197 | 1165 |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Reasoning C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 23.3 (#180), Qwen1.5-72B: 22.2 (#203)
| Benchmark | C4ai Aya Expanse 32b | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1148 |
Math Too close to call
C4ai Aya Expanse 32b: 34.0 (#197), Qwen1.5-72B: 33.2 (#205)
| Benchmark | C4ai Aya Expanse 32b | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1200 | 1164 |
Knowledge C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 33.2 (#206), Qwen1.5-72B: 11.5 (#300)
| Benchmark | C4ai Aya Expanse 32b | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1182 | 1136 |
| GPQA Diamond | — | 28.8% |
| Vectara Hallucination Rate | 10.9% | — |
Multilingual C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 38.4 (#230), Qwen1.5-72B: 33.2 (#253)
| Benchmark | C4ai Aya Expanse 32b | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1213 | 1135 |
| LMArena Chinese | 1211 | 1186 |
| LMArena French | 1248 | 1159 |
| LMArena German | 1199 | 1084 |
| LMArena Japanese | 1163 | 1061 |
| LMArena Korean | 1158 | 1050 |
| LMArena Russian | 1227 | 1104 |
| LMArena Spanish | 1193 | 1110 |
Instruction Following C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 62.6 (#237), Qwen1.5-72B: 59.3 (#256)
| Benchmark | C4ai Aya Expanse 32b | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1196 | 1141 |
Long Context C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 37.2 (#220), Qwen1.5-72B: 35.1 (#243)
| Benchmark | C4ai Aya Expanse 32b | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1228 | 1157 |
Writing & Preference C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 42.2 (#235), Qwen1.5-72B: 37.3 (#258)
| Benchmark | C4ai Aya Expanse 32b | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1224 | 1166 |
| LMArena Creative Writing | 1200 | 1137 |
| LMArena Multi-Turn | 1190 | 1160 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Qwen1.5-72B?
C4ai Aya Expanse 32b is the stronger model overall, scoring 35.9 to 30.8 on the Noometry Index.
Is C4ai Aya Expanse 32b or Qwen1.5-72B better for coding?
C4ai Aya Expanse 32b scores higher on coding benchmarks: 34.8 versus 31.9 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 32b and Qwen1.5-72B share?
17 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Qwen1.5-72B has 22.