Reasoning and Planning on Plasma
85AccuracyCoT
Evaluation Results
| Method | Links | |
|---|---|---|
| CoTBackbone=DeepSeek-V3-671B, Direct Decision=true2026.05 | 85 | |
| CoTBackbone=DeepSeek-V3-671B, Direct Decision=false2026.05 | 78.4 | |
| VanillaBackbone=DeepSeek-V3-671B, Direct Decision=true2026.05 | 78.1 | |
| VanillaBackbone=DeepSeek-V3-671B, Direct Decision=false2026.05 | 77.4 | |
| ANCHORBackbone=Qwen2.5-72B, Direct Decision=false2026.05 | 76.4 | |
| CoTBackbone=Qwen2.5-72B, Direct Decision=true2026.05 | 74.5 | |
| BIRDBackbone=Qwen2.5-72B, Direct Decision=false2026.05 | 71.8 | |
| VanillaBackbone=Qwen2.5-72B, Direct Decision=true2026.05 | 64.9 | |
| VanillaBackbone=Qwen2.5-72B, Direct Decision=false2026.05 | 60.4 | |
| CoTBackbone=Qwen2.5-72B, Direct Decision=false2026.05 | 56.5 |