Model comparison
C4ai Aya Expanse 32b vs DeepSeek-V2 (MoE-236B, May 2024)
C4ai Aya Expanse 32b has enough public results to be ranked (#221); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Cohere
DeepSeekSummary
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 34.8.
Side by side
| C4ai Aya Expanse 32b | DeepSeek-V2 (MoE-236B, May 2024) | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 35.9 | 40.3 |
| Released | 2024-10-24 | 2024-05-07 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
C4ai Aya Expanse 32b: 34.8 (#231), DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139)
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| BigCodeBench Instruct | — | 48.9% |
| LMArena Coding | 1197 | — |
| BigCodeBench Complete | — | 59.4% |
Reasoning Not comparable
C4ai Aya Expanse 32b: 23.3 (#180), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Hard Prompts | 1193 | — |
| BIG-Bench Hard | — | 78.8% |
| Epoch Capabilities Index | — | 124.77 |
| HellaSwag | — | 87.1% |
| PIQA | — | 83.9% |
| WinoGrande | — | 86.3% |
Math Not comparable
C4ai Aya Expanse 32b: 34.0 (#197), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Math | 1200 | — |
Knowledge Not comparable
C4ai Aya Expanse 32b: 33.2 (#206), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | — |
| LMArena Expert | 1182 | — |
| ARC (AI2) Challenge | — | 92.2% |
| MMLU | — | 78.4% |
| TriviaQA | — | 80% |
Multilingual Not comparable
C4ai Aya Expanse 32b: 38.4 (#230), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Non-English | 1213 | — |
| LMArena Chinese | 1211 | — |
| LMArena French | 1248 | — |
| LMArena German | 1199 | — |
| LMArena Japanese | 1163 | — |
| LMArena Korean | 1158 | — |
| LMArena Russian | 1227 | — |
| LMArena Spanish | 1193 | — |
Instruction Following Not comparable
C4ai Aya Expanse 32b: 62.6 (#237), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Instruction Following | 1196 | — |
Long Context Not comparable
C4ai Aya Expanse 32b: 37.2 (#220), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Longer Query | 1228 | — |
Writing & Preference Not comparable
C4ai Aya Expanse 32b: 42.2 (#235), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | C4ai Aya Expanse 32b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Text | 1224 | — |
| LMArena Creative Writing | 1200 | — |
| LMArena Multi-Turn | 1190 | — |
Frequently asked questions
Is C4ai Aya Expanse 32b better than DeepSeek-V2 (MoE-236B, May 2024)?
C4ai Aya Expanse 32b has enough public results to be ranked (#221); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is C4ai Aya Expanse 32b or DeepSeek-V2 (MoE-236B, May 2024) better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 34.8 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 32b and DeepSeek-V2 (MoE-236B, May 2024) share?
0 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and DeepSeek-V2 (MoE-236B, May 2024) has 10.