Tabular Classification on OK
58.9F1 ScoreCatBoost
Evaluation results
| Method | Links | |
|---|---|---|
| CatBoost2026.06 | 58.9 | |
| XGBoost2026.06 | 58.8 | |
| TabM2026.06 | 58.2 | |
| TLRDBackbone=Gemma 3-12B, Teacher Model=GPT-OSS-120B, Evaluation Protocol=Fine-tuned2026.06 | 56.1 | |
| TabPFN(v2.5)2026.06 | 55.9 | |
| TLRDBackbone=Qwen3-8B, Teacher Model=GPT-OSS-120B, Evaluation Protocol=Fine-tuned2026.06 | 55.6 | |
| TLRDBackbone=Gemma 3-12B, Teacher Model=Qwen3-Next-80B, Evaluation Protocol=Fine-tuned2026.06 | 55.6 | |
| GPT-OSS-120BEvaluation Protocol=Tri-level Reasoning2026.06 | 55 | |
| TLRDBackbone=Qwen3-8B, Teacher Model=Qwen3-Next-80B, Evaluation Protocol=Fine-tuned2026.06 | 55 | |
| GPT-OSS-20BEvaluation Protocol=Tri-level Reasoning2026.06 | 54.5 | |
| TLRDBackbone=Llama 3.1-8B, Teacher Model=GPT-OSS-120B, Evaluation Protocol=Fine-tuned2026.06 | 54.2 | |
| Qwen3-8BEvaluation Protocol=Tri-level Reasoning2026.06 | 54 | |
| Qwen3-8BEvaluation Protocol=Zero-shot2026.06 | 53.6 | |
| TLRDBackbone=Llama 3.1-8B, Teacher Model=Qwen3-Next-80B, Evaluation Protocol=Fine-tuned2026.06 | 53.2 | |
| TabPFN(v2.0)2026.06 | 52.6 | |
| Qwen3-Next-80BEvaluation Protocol=Tri-level Reasoning2026.06 | 52.6 | |
| Llama 3.1-8BEvaluation Protocol=Tri-level Reasoning2026.06 | 51.5 | |
| Gemma 3-12BEvaluation Protocol=Tri-level Reasoning2026.06 | 51.1 | |
| GPT-OSS-120BEvaluation Protocol=Zero-shot2026.06 | 50.4 | |
| Gemma 3-12BEvaluation Protocol=Zero-shot2026.06 | 50.3 | |
| GPT-OSS-20BEvaluation Protocol=Zero-shot2026.06 | 49.4 | |
| Llama 3.1-8BEvaluation Protocol=Zero-shot2026.06 | 46 | |
| Qwen3-Next-80BEvaluation Protocol=Zero-shot2026.06 | 44.5 |