Model comparison
C4ai Aya Expanse 32b vs DeepSeek Coder 1.3B
C4ai Aya Expanse 32b has enough public results to be ranked (#216); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Cohere
DeepSeekSummary
- The widest gap is in coding, where C4ai Aya Expanse 32b leads 34.3 to 30.7.
Side by side
| C4ai Aya Expanse 32b | DeepSeek Coder 1.3B | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 35.3 | 34.5 |
| Released | 2024-10-24 | 2023-11-02 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 9 |
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: 34.3 (#227), DeepSeek Coder 1.3B: 30.7 (#282)
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 1.3B |
|---|---|---|
| BigCodeBench Instruct | — | 22.8% |
| LMArena Coding | 1197 | — |
| BigCodeBench Complete | — | 29.6% |
| HumanEval+ | — | 60.4% |
| MBPP+ | — | 54.8% |
Reasoning Not comparable
C4ai Aya Expanse 32b: 22.3 (#183), DeepSeek Coder 1.3B: —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Hard Prompts | 1193 | — |
| Epoch Capabilities Index | — | 62.18 |
| WinoGrande | — | 53.3% |
Math Not comparable
C4ai Aya Expanse 32b: 31.4 (#195), DeepSeek Coder 1.3B: —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Math | 1200 | — |
| GSM8K | — | 4.4% |
Knowledge Not comparable
C4ai Aya Expanse 32b: 32.6 (#202), DeepSeek Coder 1.3B: —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 1.3B |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | — |
| LMArena Expert | 1182 | — |
| ARC (AI2) Challenge | — | 25.4% |
| MMLU | — | 25.8% |
Multilingual Not comparable
C4ai Aya Expanse 32b: 38.5 (#225), DeepSeek Coder 1.3B: —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Non-English | 1213 | — |
| LMArena Chinese | 1210 | — |
| LMArena French | 1247 | — |
| LMArena German | 1199 | — |
| LMArena Japanese | 1163 | — |
| LMArena Korean | 1158 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1193 | — |
Instruction Following Not comparable
C4ai Aya Expanse 32b: 62.9 (#232), DeepSeek Coder 1.3B: —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Instruction Following | 1196 | — |
Long Context Not comparable
C4ai Aya Expanse 32b: 37.2 (#215), DeepSeek Coder 1.3B: —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Longer Query | 1228 | — |
Writing & Preference Not comparable
C4ai Aya Expanse 32b: 42.4 (#230), DeepSeek Coder 1.3B: —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 1.3B |
|---|---|---|
| LMArena Text | 1224 | — |
| LMArena Creative Writing | 1200 | — |
| LMArena Multi-Turn | 1190 | — |
Frequently asked questions
Is C4ai Aya Expanse 32b better than DeepSeek Coder 1.3B?
C4ai Aya Expanse 32b has enough public results to be ranked (#216); DeepSeek Coder 1.3B does not yet, so treat this comparison as directional.
Is C4ai Aya Expanse 32b or DeepSeek Coder 1.3B better for coding?
C4ai Aya Expanse 32b scores higher on coding benchmarks: 34.3 versus 30.7 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 32b and DeepSeek Coder 1.3B share?
0 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and DeepSeek Coder 1.3B has 9.