RTL Design Code Generation on CVDP cid03
39Function AccuracyClaude-3.7
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Claude-3.7Evaluation Protocol=Original pass@12026.05 | 39 | — | |
| Claude-3.7Evaluation Protocol=RTL-BenchMT fixes2026.05 | 39 | — | |
| GPT-4oEvaluation Protocol=Original pass@12026.05 | 35.1 | — | |
| GPT-4oEvaluation Protocol=RTL-BenchMT fixes2026.05 | 33.8 | — | |
| LlaMA-405BEvaluation Protocol=Original pass@12026.05 | 27.3 | — | |
| GPT-4o-miniEvaluation Protocol=Original pass@12026.05 | 18.1 | — | |
| QwQ-32BEvaluation Protocol=Original pass@12026.05 | 14.3 | — | |
| LlaMA-70BEvaluation Protocol=Original pass@12026.05 | 12.3 | — |