Solvent Prediction on ChemCoTBench
57.8Top-1 SimilarityChemMAS
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| ChemMAS2025.09 | 57.8 | 66.5 | 76.8 | |
| GPT5Evaluation Protocol=Zero-shot2025.09 | 44.1 | 57.5 | 65.2 | |
| Gemini2.5-ProEvaluation Protocol=Zero-shot2025.09 | 42.1 | 58.6 | 71.2 | |
| Claude3.7-SonnetEvaluation Protocol=Zero-shot2025.09 | 40.4 | 52.1 | 61.2 | |
| DeepSeek-R1Evaluation Protocol=Zero-shot2025.09 | 38.4 | 48.3 | 56.3 | |
| Qwen3-235B-A22BEvaluation Protocol=Zero-shot2025.09 | 36.4 | 41.1 | 52.9 |