Educational Content Generation Evaluation on Educational Content Evaluation Scenarios
4.03Groundedness (GT)InnoSpark
Evaluation Results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| InnoSpark2026.06 | 4.03 | 3.98 | 3.93 | 4.03 | 3.95 | 3.67 | 3.97 | 4.08 | 3.98 | |
| Gemini-2.5-Pro2026.06 | 3.93 | 4.07 | 4.5 | 3.94 | 3.81 | 3.57 | 3.68 | 3.97 | 3.92 | |
| GPT-4o2026.06 | 3.45 | 2.81 | 3.39 | 3.45 | 3.48 | 3.17 | 3.51 | 3.5 | 3.41 | |
| DeepSeek-R1-03252026.06 | 2.76 | 3.96 | 4.26 | 3.16 | 3.34 | 2.97 | 3.22 | 3.66 | 3.53 |