Problem list generation on Problem List
35.61Composite ScoreSLERP Merge
Evaluation results
| Method | Links | |
|---|---|---|
| SLERP MergeEvaluation protocol=SFT2026.04 | 35.61 | |
| GatorTronLlama_SFTEvaluation protocol=SFT2026.04 | 33.85 | |
| GatorTronLlamaEvaluation protocol=SFT2026.04 | 33.07 | |
| Llama-3.1-8B-InstructEvaluation protocol=SFT2026.04 | 33.05 | |
| Linear MergeEvaluation protocol=SFT2026.04 | 31.47 | |
| SLERP MergeEvaluation protocol=0-shot2026.04 | 23.4 | |
| GatorTronLlama_SFTEvaluation protocol=0-shot2026.04 | 21.53 | |
| Linear MergeEvaluation protocol=0-shot2026.04 | 21.17 | |
| GatorTronLlamaEvaluation protocol=0-shot2026.04 | 20.84 | |
| Llama-3.1-8B-InstructEvaluation protocol=0-shot2026.04 | 19.05 |