Model comparison
C4ai Aya Expanse 8b vs DeepSeek-V2 (MoE-236B, May 2024)
C4ai Aya Expanse 8b has enough public results to be ranked (#227); 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 39.8 to 33.2.
Side by side
| C4ai Aya Expanse 8b | DeepSeek-V2 (MoE-236B, May 2024) | |
|---|---|---|
| Provider | Cohere | DeepSeek |
| Noometry Index | 34.3 | 39.7 |
| Released | 2024-10-24 | 2024-05-07 |
| Weights | Open | Open |
| Context window | 8K | — |
| Max output | 4K | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 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 8b: 33.2 (#252), DeepSeek-V2 (MoE-236B, May 2024): 39.8 (#141)
| Benchmark | C4ai Aya Expanse 8b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| BigCodeBench Instruct | — | 48.9% |
| LMArena Coding | 1161 | — |
| BigCodeBench Complete | — | 59.4% |
Reasoning Not comparable
C4ai Aya Expanse 8b: 21.4 (#198), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | C4ai Aya Expanse 8b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Hard Prompts | 1156 | — |
| BIG-Bench Hard | — | 78.8% |
| Epoch Capabilities Index | — | 124.78 |
| HellaSwag | — | 87.1% |
| PIQA | — | 83.9% |
| WinoGrande | — | 86.3% |
Math Not comparable
C4ai Aya Expanse 8b: 30.8 (#204), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | C4ai Aya Expanse 8b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Math | 1168 | — |
Knowledge Not comparable
C4ai Aya Expanse 8b: 33.0 (#197), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | C4ai Aya Expanse 8b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | — |
| LMArena Expert | 1153 | — |
| ARC (AI2) Challenge | — | 92.2% |
| MMLU | — | 78.4% |
| TriviaQA | — | 80% |
Multilingual Not comparable
C4ai Aya Expanse 8b: 36.3 (#237), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | C4ai Aya Expanse 8b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Non-English | 1180 | — |
| LMArena Chinese | 1181 | — |
| LMArena German | 1188 | — |
| LMArena Japanese | 1120 | — |
| LMArena Russian | 1197 | — |
Instruction Following Not comparable
C4ai Aya Expanse 8b: 60.4 (#248), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | C4ai Aya Expanse 8b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Instruction Following | 1155 | — |
Long Context Not comparable
C4ai Aya Expanse 8b: 36.1 (#231), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | C4ai Aya Expanse 8b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Longer Query | 1192 | — |
Writing & Preference Not comparable
C4ai Aya Expanse 8b: 39.2 (#245), DeepSeek-V2 (MoE-236B, May 2024): —
| Benchmark | C4ai Aya Expanse 8b | DeepSeek-V2 (MoE-236B, May 2024) |
|---|---|---|
| LMArena Text | 1185 | — |
| LMArena Creative Writing | 1168 | — |
| LMArena Multi-Turn | 1160 | — |
Frequently asked questions
Is C4ai Aya Expanse 8b better than DeepSeek-V2 (MoE-236B, May 2024)?
C4ai Aya Expanse 8b has enough public results to be ranked (#227); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is C4ai Aya Expanse 8b or DeepSeek-V2 (MoE-236B, May 2024) better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 39.8 versus 33.2 in the Noometry coding category.
How many benchmarks do C4ai Aya Expanse 8b and DeepSeek-V2 (MoE-236B, May 2024) share?
0 benchmarks have published results for both models. C4ai Aya Expanse 8b has 15 scored results on Noometry and DeepSeek-V2 (MoE-236B, May 2024) has 10.