List your company

Reasoning on Reasoning Domain Game

61.3ScoreSTEER2ADAPT
46.147250.081154.01557.9489Feb 7, 2026

Evaluation results

MethodLinks
STEER2ADAPTBackbone=Qwen-2.5-7B-Instruct2026.0261.3
Direct InferenceBackbone=Qwen-2.5-7B-Instruct2026.0259.62
Few-ShotBackbone=Qwen-2.5-7B-Instruct, n=22026.0259.21
REPBackbone=Qwen-2.5-7B-Instruct2026.0259.11
Few-ShotBackbone=Qwen-2.5-7B-Instruct, n=12026.0258.81
STEER2ADAPTBackbone=Llama-3.1-8B-Instruct2026.0258
CAABackbone=Qwen-2.5-7B-Instruct2026.0256.99
ICLBackbone=Qwen-2.5-7B-Instruct2026.0255.83
REPBackbone=Llama-3.1-8B-Instruct2026.0255.37
Few-ShotBackbone=Llama-3.1-8B-Instruct, n=22026.0255.13
Direct InferenceBackbone=Llama-3.1-8B-Instruct2026.0253.95
Few-ShotBackbone=Llama-3.1-8B-Instruct, n=12026.0252.8
CAABackbone=Llama-3.1-8B-Instruct2026.0251.44
ICLBackbone=Llama-3.1-8B-Instruct2026.0251.25
CAABackbone=Mistral-7B-Instruct-v0.12026.0250.87
STEER2ADAPTBackbone=Mistral-7B-Instruct-v0.12026.0250.33
REPBackbone=Mistral-7B-Instruct-v0.12026.0249.77
Few-ShotBackbone=Mistral-7B-Instruct-v0.1, n=12026.0249.69
Few-ShotBackbone=Mistral-7B-Instruct-v0.1, n=22026.0249.69
Direct InferenceBackbone=Mistral-7B-Instruct-v0.12026.0248.89
ICLBackbone=Mistral-7B-Instruct-v0.12026.0246.73