Model comparison
C4ai Aya Expanse 32b vs DeepSeek Coder 33B
C4ai Aya Expanse 32b has enough public results to be ranked (#216); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Cohere
DeepSeekSummary
- The widest gap is in coding, where DeepSeek Coder 33B leads 37.4 to 34.3.
Side by side
| C4ai Aya Expanse 32b | DeepSeek Coder 33B | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 35.3 | 38.3 |
| 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 DeepSeek Coder 33B leads
C4ai Aya Expanse 32b: 34.3 (#227), DeepSeek Coder 33B: 37.4 (#180)
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 33B |
|---|---|---|
| BigCodeBench Instruct | — | 42% |
| LMArena Coding | 1197 | — |
| BigCodeBench Complete | — | 51.1% |
| HumanEval+ | — | 75% |
| MBPP+ | — | 70.1% |
Reasoning Not comparable
C4ai Aya Expanse 32b: 22.3 (#183), DeepSeek Coder 33B: —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 33B |
|---|---|---|
| LMArena Hard Prompts | 1193 | — |
| Epoch Capabilities Index | — | 95.74 |
| WinoGrande | — | 62% |
Math Not comparable
C4ai Aya Expanse 32b: 31.4 (#195), DeepSeek Coder 33B: —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 33B |
|---|---|---|
| LMArena Math | 1200 | — |
| GSM8K | — | 35.4% |
Knowledge Not comparable
C4ai Aya Expanse 32b: 32.6 (#202), DeepSeek Coder 33B: —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 33B |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | — |
| LMArena Expert | 1182 | — |
| ARC (AI2) Challenge | — | 42.2% |
| MMLU | — | 39.4% |
Multilingual Not comparable
C4ai Aya Expanse 32b: 38.5 (#225), DeepSeek Coder 33B: —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 33B |
|---|---|---|
| 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 33B: —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 33B |
|---|---|---|
| LMArena Instruction Following | 1196 | — |
Long Context Not comparable
C4ai Aya Expanse 32b: 37.2 (#215), DeepSeek Coder 33B: —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 33B |
|---|---|---|
| LMArena Longer Query | 1228 | — |
Writing & Preference Not comparable
C4ai Aya Expanse 32b: 42.4 (#230), DeepSeek Coder 33B: —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek Coder 33B |
|---|---|---|
| LMArena Text | 1224 | — |
| LMArena Creative Writing | 1200 | — |
| LMArena Multi-Turn | 1190 | — |
Frequently asked questions
Is C4ai Aya Expanse 32b better than DeepSeek Coder 33B?
C4ai Aya Expanse 32b has enough public results to be ranked (#216); DeepSeek Coder 33B does not yet, so treat this comparison as directional.
Is C4ai Aya Expanse 32b or DeepSeek Coder 33B better for coding?
DeepSeek Coder 33B scores higher on coding benchmarks: 37.4 versus 34.3 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 32b and DeepSeek Coder 33B share?
0 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and DeepSeek Coder 33B has 9.