Reasoning/Planning on Today
81.7AccuracyANCHOR
Evaluation Results
| Method | Links | |
|---|---|---|
| ANCHORBackbone=Qwen2.5-72B, Direct Decision=false2026.05 | 81.7 | |
| CoTBackbone=DeepSeek-V3-671B, Direct Decision=true2026.05 | 80.3 | |
| CoTBackbone=DeepSeek-V3-671B, Direct Decision=false2026.05 | 78.3 | |
| BIRDBackbone=Qwen2.5-72B, Direct Decision=false2026.05 | 75.4 | |
| CoTBackbone=Qwen2.5-72B, Direct Decision=true2026.05 | 71.3 | |
| VanillaBackbone=DeepSeek-V3-671B, Direct Decision=false2026.05 | 71 | |
| VanillaBackbone=DeepSeek-V3-671B, Direct Decision=true2026.05 | 64.7 | |
| VanillaBackbone=Qwen2.5-72B, Direct Decision=true2026.05 | 59.7 | |
| CoTBackbone=Qwen2.5-72B, Direct Decision=false2026.05 | 59.3 | |
| VanillaBackbone=Qwen2.5-72B, Direct Decision=false2026.05 | 58.3 |