Reading Comprehension on DROP (test) (Accuracy and Cost)
81.7AccuracyAgentSlimming
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| AgentSlimming2026.05 | 81.7 | 0.001 | |
| AFlow2026.05 | 78.7 | 0.0016 | |
| ADAS2026.05 | 78.6 | 0.0031 | |
| CoT2026.05 | 75.9 | 0.0004 | |
| LLM-Debate2026.05 | 75.6 | 0.0029 | |
| SC-CoT2026.05 | 75.3 | 0.0024 | |
| Self-Refine2026.05 | 75 | 0.0008 |