Reasoning on Reasoning Domain Game
61.3ScoreSTEER2ADAPT
Evaluation Results
| Method | Links | |
|---|---|---|
| STEER2ADAPTBackbone=Qwen-2.5-7B-Instruct2026.02 | 61.3 | |
| Direct InferenceBackbone=Qwen-2.5-7B-Instruct2026.02 | 59.62 | |
| Few-ShotBackbone=Qwen-2.5-7B-Instruct, n=22026.02 | 59.21 | |
| REPBackbone=Qwen-2.5-7B-Instruct2026.02 | 59.11 | |
| Few-ShotBackbone=Qwen-2.5-7B-Instruct, n=12026.02 | 58.81 | |
| STEER2ADAPTBackbone=Llama-3.1-8B-Instruct2026.02 | 58 | |
| CAABackbone=Qwen-2.5-7B-Instruct2026.02 | 56.99 | |
| ICLBackbone=Qwen-2.5-7B-Instruct2026.02 | 55.83 | |
| REPBackbone=Llama-3.1-8B-Instruct2026.02 | 55.37 | |
| Few-ShotBackbone=Llama-3.1-8B-Instruct, n=22026.02 | 55.13 | |
| Direct InferenceBackbone=Llama-3.1-8B-Instruct2026.02 | 53.95 | |
| Few-ShotBackbone=Llama-3.1-8B-Instruct, n=12026.02 | 52.8 | |
| CAABackbone=Llama-3.1-8B-Instruct2026.02 | 51.44 | |
| ICLBackbone=Llama-3.1-8B-Instruct2026.02 | 51.25 | |
| CAABackbone=Mistral-7B-Instruct-v0.12026.02 | 50.87 | |
| STEER2ADAPTBackbone=Mistral-7B-Instruct-v0.12026.02 | 50.33 | |
| REPBackbone=Mistral-7B-Instruct-v0.12026.02 | 49.77 | |
| Few-ShotBackbone=Mistral-7B-Instruct-v0.1, n=12026.02 | 49.69 | |
| Few-ShotBackbone=Mistral-7B-Instruct-v0.1, n=22026.02 | 49.69 | |
| Direct InferenceBackbone=Mistral-7B-Instruct-v0.12026.02 | 48.89 | |
| ICLBackbone=Mistral-7B-Instruct-v0.12026.02 | 46.73 |