Model comparison
C4ai Aya Expanse 32b vs Deepseek Coder v2
C4ai Aya Expanse 32b and Deepseek Coder v2 score almost the same on the Noometry Index (35.9 vs 35.9), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
Cohere
DeepSeekSummary
- They share 17 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 5 categories and Deepseek Coder v2 in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where C4ai Aya Expanse 32b leads 42.2 to 38.2.
Side by side
| C4ai Aya Expanse 32b | Deepseek Coder v2 | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 35.9 | 35.9 |
| Released | 2024-10-24 | 2024-06-17 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
C4ai Aya Expanse 32b: 34.8 (#231), Deepseek Coder v2: 38.1 (#183)
| Benchmark | C4ai Aya Expanse 32b | Deepseek Coder v2 |
|---|---|---|
| LMArena Coding | 1197 | 1251 |
| BigCodeBench Instruct | — | 48.2% |
| BigCodeBench Complete | — | 59.7% |
| HumanEval+ | — | 82.3% |
| MBPP+ | — | 75.1% |
Reasoning Too close to call
C4ai Aya Expanse 32b: 23.3 (#180), Deepseek Coder v2: 23.6 (#176)
| Benchmark | C4ai Aya Expanse 32b | Deepseek Coder v2 |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1207 |
| WinoGrande | — | 83.7% |
Math Too close to call
C4ai Aya Expanse 32b: 34.0 (#197), Deepseek Coder v2: 34.9 (#190)
| Benchmark | C4ai Aya Expanse 32b | Deepseek Coder v2 |
|---|---|---|
| LMArena Math | 1200 | 1241 |
| GSM8K | — | 94.5% |
Knowledge Too close to call
C4ai Aya Expanse 32b: 33.2 (#206), Deepseek Coder v2: 32.3 (#212)
| Benchmark | C4ai Aya Expanse 32b | Deepseek Coder v2 |
|---|---|---|
| LMArena Expert | 1182 | 1181 |
| Vectara Hallucination Rate | 10.9% | — |
| ARC (AI2) Challenge | — | 64.3% |
Multilingual C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 38.4 (#230), Deepseek Coder v2: 36.3 (#240)
| Benchmark | C4ai Aya Expanse 32b | Deepseek Coder v2 |
|---|---|---|
| LMArena Non-English | 1213 | 1182 |
| LMArena Chinese | 1211 | 1201 |
| LMArena French | 1248 | 1185 |
| LMArena German | 1199 | 1164 |
| LMArena Japanese | 1163 | 1126 |
| LMArena Korean | 1158 | 1104 |
| LMArena Russian | 1227 | 1188 |
| LMArena Spanish | 1193 | 1153 |
Instruction Following Too close to call
C4ai Aya Expanse 32b: 62.6 (#237), Deepseek Coder v2: 61.7 (#242)
| Benchmark | C4ai Aya Expanse 32b | Deepseek Coder v2 |
|---|---|---|
| LMArena Instruction Following | 1196 | 1180 |
Long Context Too close to call
C4ai Aya Expanse 32b: 37.2 (#220), Deepseek Coder v2: 37.0 (#224)
| Benchmark | C4ai Aya Expanse 32b | Deepseek Coder v2 |
|---|---|---|
| LMArena Longer Query | 1228 | 1219 |
Writing & Preference C4ai Aya Expanse 32b leads
C4ai Aya Expanse 32b: 42.2 (#235), Deepseek Coder v2: 38.2 (#253)
| Benchmark | C4ai Aya Expanse 32b | Deepseek Coder v2 |
|---|---|---|
| LMArena Text | 1224 | 1191 |
| LMArena Creative Writing | 1200 | 1120 |
| LMArena Multi-Turn | 1190 | 1177 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than Deepseek Coder v2?
C4ai Aya Expanse 32b and Deepseek Coder v2 score almost the same on the Noometry Index (35.9 vs 35.9), so choose on price, context window or the category you care about most.
Is C4ai Aya Expanse 32b or Deepseek Coder v2 better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 34.8 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 32b and Deepseek Coder v2 share?
17 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and Deepseek Coder v2 has 24.