Knowledge Tracing on DBE-KT22 (test)
79.8AUCAKT
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| AKTtraining=traditional, design=–2026.01 | 79.8 | — | — | |
| DKVMNtraining=traditional, design=–2026.01 | 78.3 | — | — | |
| DKTtraining=traditional, design=–2026.01 | 78.2 | — | — | |
| Gemini-2.5-flashdesign=Option, framework=Thinking-KT2026.01 | 71.85 | 76.64 | 84.46 | |
| Gemini-2.5-flashdesign=No-Option, framework=Thinking-KT2026.01 | 71.22 | 73.62 | 82.08 | |
| Gemini-2.5-flashdesign=No-Option, framework=LLM-based (No-Think)2026.01 | 71.05 | 75.27 | 83.33 | |
| Gemini-2.5-flashdesign=Weight, framework=LLM-based (No-Think)2026.01 | 71.05 | 75.27 | 83.33 | |
| Gemini-2.5-flashdesign=Option, framework=LLM-based (No-Think)2026.01 | 69.99 | 74.45 | 82.68 | |
| Gemini-2.5-flashdesign=Weight, framework=Thinking-KT2026.01 | 69.69 | 73.88 | 82.19 | |
| Qwen3-1.7Bdesign=No-Option, framework=Thinking-KT2026.01 | 69.58 | 73.9 | 82.76 | |
| Qwen3-1.7Bdesign=Option, framework=Thinking-KT2026.01 | 65.97 | 69.78 | 80.57 | |
| GPT-5-minidesign=No-Option, framework=Thinking-KT2026.01 | 63.87 | 77.19 | 85.76 | |
| GPT-5-minidesign=Option, framework=Thinking-KT2026.01 | 63.67 | 76.37 | 85.22 | |
| GPT-5-minidesign=Weight, framework=Thinking-KT2026.01 | 63.27 | 76.92 | 85.36 | |
| Qwen3-1.7Bdesign=Weight, framework=Thinking-KT2026.01 | 59.53 | 73.35 | 83.36 | |
| GPT-5-minidesign=No-Option, framework=LLM-based (No-Think)2026.01 | 58.75 | 34.71 | 29.25 | |
| GPT-5-minidesign=Option, framework=LLM-based (No-Think)2026.01 | 58.18 | 32.69 | 24.14 | |
| GPT-5-minidesign=Weight, framework=LLM-based (No-Think)2026.01 | 57.5 | 29.94 | 17.47 | |
| Qwen3-1.7Bdesign=Option, framework=LLM-based (No-Think)2026.01 | 52.62 | 75.55 | 85.81 | |
| Qwen3-1.7Bdesign=No-Option, framework=LLM-based (No-Think)2026.01 | 52.16 | 72.53 | 83.77 | |
| Qwen3-1.7Bdesign=Weight, framework=LLM-based (No-Think)2026.01 | 50.39 | 76.1 | 86.43 |