Clinical generation on ACI-Bench
40.99Composite ScoreSLERP Merge
Evaluation Results
| Method | Links | |
|---|---|---|
| SLERP MergeEvaluation protocol=SFT2026.04 | 40.99 | |
| GatorTronLlama_SFTEvaluation protocol=SFT2026.04 | 39.28 | |
| Linear MergeEvaluation protocol=SFT2026.04 | 38.83 | |
| GatorTronLlamaEvaluation protocol=SFT2026.04 | 36.85 | |
| Llama-3.1-8B-InstructEvaluation protocol=SFT2026.04 | 36.71 | |
| SLERP MergeEvaluation protocol=0-shot2026.04 | 31.94 | |
| Linear MergeEvaluation protocol=0-shot2026.04 | 30.58 | |
| Llama-3.1-8B-InstructEvaluation protocol=0-shot2026.04 | 29.95 | |
| GatorTronLlama_SFTEvaluation protocol=0-shot2026.04 | 29.69 | |
| GatorTronLlamaEvaluation protocol=0-shot2026.04 | 28.54 |