General Reasoning Generalization on Comprehensive Reasoning Suite
63.88Average ScoreGHS-TDA
Evaluation Results
| Method | Links | |
|---|---|---|
| GHS-TDABackbone=Llama 3-8B2026.02 | 63.88 | |
| AoTBackbone=Llama 3-8B2026.02 | 62.82 | |
| GHS-TDABackbone=Qwen 2-14B2026.02 | 62.35 | |
| GoTBackbone=Llama 3-8B2026.02 | 61.1 | |
| ToTBackbone=Llama 3-8B2026.02 | 60.85 | |
| AoTBackbone=Qwen 2-14B2026.02 | 60.81 | |
| ToTBackbone=Qwen 2-14B2026.02 | 59.66 | |
| GoTBackbone=Qwen 2-14B2026.02 | 59.62 | |
| CoTBackbone=Llama 3-8B2026.02 | 56.99 | |
| CoTBackbone=Qwen 2-14B2026.02 | 55.6 |