DeepSeek-Coder-V2-Lite-Base
DeepSeek-Coder-V2-Lite-Base.
Released June 13th, 2024 Compare with others
5
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Unknown lab Jun 2024
DeepSeek-Coder-V2-Lite-Base
99.7
#215 of 256
Epoch Capabilities Index
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ARC-Challenge | 57.3% | #36 of 75 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI | |
| MMLU | 60.5% | #42 of 85 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI | |
| WinoGrande | 72.9% | #41 of 76 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI | |
| MMLU-Pro | 34.4% | #172 of 212 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 67.1% | #25 of 70 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI |
The lab's models over time
's models in color, against every other model on the Epoch Capabilities Index, by release date.
Source: Epoch Capabilities Index, Epoch AI (CC BY 4.0)