Documentation Generation on PyMedPhys
4.68Final Score (Avg)gemini-2.5-pro
Evaluation Results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| gemini-2.5-pro2026.05 | 4.68 | 4.52 | 4.4 | 4.8 | 4.55 | 4.67 | 4.87 | 4.4 | 3.52 | 4.63 | 4.88 | |
| gemini-2.5-flash2026.05 | 4.65 | 4.45 | 4.38 | 4.36 | 4.47 | 4.65 | 4.95 | 4.45 | 3.3 | 4.55 | 4.97 | |
| gpt-5-nano2026.05 | 3.7 | 3.89 | 3.97 | 4.5 | 3.82 | 4.36 | 4.73 | 3.16 | 2.43 | 3.55 | 4.53 | |
| qwen3-30b-a3b2026.05 | 3.55 | 3.5 | 3.67 | 4.17 | 3.4 | 2.17 | 4.32 | 3.37 | 2.67 | 3.42 | 4.32 | |
| qwen3-32b2026.05 | 3.36 | 3.44 | 3.58 | 4.03 | 3.3 | 3.1 | 4.25 | 3.15 | 2.2 | 3.2 | 4.15 | |
| gpt-4.1-nano2026.05 | 3.15 | 3.46 | 3.7 | 3.97 | 3.28 | 3.67 | 4.07 | 3.58 | 1.23 | 3.71 | 3.9 | |
| llama-3.2-11b2026.05 | 2.85 | 3.15 | 3.27 | 3.92 | 2.85 | 2.12 | 4.15 | 2.75 | 2.22 | 3.05 | 4.02 | |
| llama-4-scout2026.05 | 2.7 | 2.9 | 2.8 | 3.55 | 2.57 | 1.67 | 3.8 | 2.5 | 2.8 | 3.02 | 3.42 |