Physics Word Problem Generation on Physics Word Problems Kinematics Topic (test)
94.15Solvability (%)ChatGPT-3.5-Turbo
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| ChatGPT-3.5-Turbo2026.06 | 94.15 | 0.37 | 0.48 | |
| DeepSeek-R12026.06 | 93.79 | 0.42 | 0.55 | |
| ARVRE2026.06 | 91.38 | 1.56 | 1.75 | |
| Mistral-7B-Instruct-v0.22026.06 | 90.14 | 0.22 | 0.24 | |
| Llama-3.2-3B-Instruct2026.06 | 89.28 | 0.25 | 0.42 |