DeepSeek Coder 33B
DeepSeek Coder 33B.
6
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
DeepSeek Nov 2023 DeepSeek Coder 33B
Open weights
76.6
#239 of 256
Epoch Capabilities Index
- AutoCodeBench 28.5% #28 /34
- CodeEditorBench 73.7% #4 /7
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 | 42.2% | #56 of 75 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI | |
| MMLU | 39.4% | #69 of 85 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI | |
| WinoGrande | 62% | #64 of 76 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 35.4% | #47 of 70 | Claim in Qwen2.5-Coder Technical Report, via Epoch AI |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CodeEditorBench | 73.7% | #4 of 7 | Official leaderboard | |
| AutoCodeBench | 28.5% | #28 of 34 | Official leaderboard |
DeepSeek's models over time
DeepSeek'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)