Code Generation on QHack 2023
61Pass@1PennySynth-13k
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PennySynth-13kModel=Claude Sonnet 4.62026.05 | 61 | 68 | |
| PennySynth-13kModel=GPT-5.52026.05 | 50 | 57 | |
| PennySynth-13kModel=Qwen3-235B2026.05 | 50 | 61 | |
| PennySynth-13kModel=DeepSeek-V32026.05 | 36 | 36 | |
| PennySynth-13kModel=GLM-5.12026.05 | 11 | 32 | |
| PennySynth-13kModel=LLaMA 3.1-8B2026.05 | 11 | 32 | |
| PennySynth-13kModel=Gemini 2.5 Pro2026.05 | 4 | 4 |