Curiosity Self-Report Assessment on 5DCR
7Joyous ExplorationDeepSeek-V3.1
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| DeepSeek-V3.12025.10 | 7 | 5.94 | 3.92 | 4.38 | 6.01 | 5.53 | |
| Gemma3-12B2025.10 | 6.75 | 6.23 | 3.98 | 4.58 | 6.25 | 5 | |
| GPT-4o2025.10 | 6.58 | 6.2 | 4.4 | 4.71 | 6.25 | 5 | |
| Qwen2.5-7B2025.10 | 6.25 | 5.6 | 4.18 | 4.4 | 5.5 | 4.15 | |
| Gemini-2.5-Flash2025.10 | 6.08 | 4.9 | 3.45 | 1.58 | 4.88 | 2.9 | |
| Qwen2.5-32B2025.10 | 5.65 | 4.75 | 4.25 | 4.06 | 4.6 | 4.1 | |
| Llama3-8B2025.10 | 5.6 | 5.45 | 3.75 | 4.18 | 5.28 | 3.6 | |
| InternLM3-8B2025.10 | 5.58 | 5.58 | 4.33 | 4.13 | 5.8 | 4.53 | |
| Qwen2.5-14B2025.10 | 5.03 | 4.93 | 3.88 | 4.32 | 5 | 4.45 | |
| Human2025.10 | 5.03 | 4.54 | 5.36 | 4.93 | 4.86 | 4.16 |