Agentic Reasoning on τ-Bench
62.58ScoreIOA
Evaluation Results
| Method | Links | |
|---|---|---|
| IOATeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-14B2026.02 | 62.58 | |
| IOATeacher LLM=OpenAI o1, Student Model (SLM)=Q-14B2026.02 | 61.14 | |
| IOATeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-7B2026.02 | 60.44 | |
| MADATeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-14B2026.02 | 59.22 | |
| IOATeacher LLM=OpenAI o1, Student Model (SLM)=Q-7B2026.02 | 59.02 | |
| Star-AgentsTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-14B2026.02 | 58.37 | |
| MADATeacher LLM=OpenAI o1, Student Model (SLM)=Q-14B2026.02 | 57.86 | |
| CasCoDTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-14B2026.02 | 57.16 | |
| IOATeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-3B2026.02 | 57.09 | |
| MADATeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-7B2026.02 | 57.03 | |
| Star-AgentsTeacher LLM=OpenAI o1, Student Model (SLM)=Q-14B2026.02 | 56.92 | |
| DSSTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-14B2026.02 | 56.54 | |
| CounterDistillTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-14B2026.02 | 56.42 | |
| Star-AgentsTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-7B2026.02 | 56.11 | |
| CasCoDTeacher LLM=OpenAI o1, Student Model (SLM)=Q-14B2026.02 | 55.94 | |
| MADATeacher LLM=OpenAI o1, Student Model (SLM)=Q-7B2026.02 | 55.77 | |
| LionTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-14B2026.02 | 55.73 | |
| IOATeacher LLM=DeepSeek-R1, Student Model (SLM)=L-8B2026.02 | 55.66 | |
| IOATeacher LLM=OpenAI o1, Student Model (SLM)=Q-3B2026.02 | 55.63 | |
| DSSTeacher LLM=OpenAI o1, Student Model (SLM)=Q-14B2026.02 | 55.38 | |
| CounterDistillTeacher LLM=OpenAI o1, Student Model (SLM)=Q-14B2026.02 | 55.11 | |
| CasCoDTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-7B2026.02 | 55.03 | |
| Star-AgentsTeacher LLM=OpenAI o1, Student Model (SLM)=Q-7B2026.02 | 54.85 | |
| LionTeacher LLM=OpenAI o1, Student Model (SLM)=Q-14B2026.02 | 54.56 | |
| LaMiniTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-14B2026.02 | 54.52 | |
| DSSTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-7B2026.02 | 54.41 | |
| CounterDistillTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-7B2026.02 | 54.28 | |
| CasCoDTeacher LLM=OpenAI o1, Student Model (SLM)=Q-7B2026.02 | 53.96 | |
| IOATeacher LLM=OpenAI o1, Student Model (SLM)=L-8B2026.02 | 53.84 | |
| MADATeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-3B2026.02 | 53.81 | |
| LionTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-7B2026.02 | 53.58 | |
| LaMiniTeacher LLM=OpenAI o1, Student Model (SLM)=Q-14B2026.02 | 53.42 | |
| DSSTeacher LLM=OpenAI o1, Student Model (SLM)=Q-7B2026.02 | 53.41 | |
| Self-InstructTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-14B2026.02 | 53.41 | |
| CounterDistillTeacher LLM=OpenAI o1, Student Model (SLM)=Q-7B2026.02 | 53.27 | |
| Star-AgentsTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-3B2026.02 | 52.96 | |
| LionTeacher LLM=OpenAI o1, Student Model (SLM)=Q-7B2026.02 | 52.57 | |
| MADATeacher LLM=OpenAI o1, Student Model (SLM)=Q-3B2026.02 | 52.48 | |
| LaMiniTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-7B2026.02 | 52.37 | |
| Self-InstructTeacher LLM=OpenAI o1, Student Model (SLM)=Q-14B2026.02 | 52.31 | |
| MADATeacher LLM=DeepSeek-R1, Student Model (SLM)=L-8B2026.02 | 52.31 | |
| CasCoDTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-3B2026.02 | 51.84 | |
| Star-AgentsTeacher LLM=OpenAI o1, Student Model (SLM)=Q-3B2026.02 | 51.72 | |
| Self-InstructTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-7B2026.02 | 51.42 | |
| Star-AgentsTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-8B2026.02 | 51.42 | |
| LaMiniTeacher LLM=OpenAI o1, Student Model (SLM)=Q-7B2026.02 | 51.36 | |
| DSSTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-3B2026.02 | 51.26 | |
| CounterDistillTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-3B2026.02 | 51.05 | |
| IOATeacher LLM=DeepSeek-R1, Student Model (SLM)=L-3B2026.02 | 50.98 | |
| MADATeacher LLM=OpenAI o1, Student Model (SLM)=L-8B2026.02 | 50.67 | |
| CasCoDTeacher LLM=OpenAI o1, Student Model (SLM)=Q-3B2026.02 | 50.66 | |
| LionTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-3B2026.02 | 50.42 | |
| CasCoDTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-8B2026.02 | 50.35 | |
| Self-InstructTeacher LLM=OpenAI o1, Student Model (SLM)=Q-7B2026.02 | 50.27 | |
| DSSTeacher LLM=OpenAI o1, Student Model (SLM)=Q-3B2026.02 | 50.14 | |
| Star-AgentsTeacher LLM=OpenAI o1, Student Model (SLM)=L-8B2026.02 | 49.88 | |
| CounterDistillTeacher LLM=OpenAI o1, Student Model (SLM)=Q-3B2026.02 | 49.87 | |
| DSSTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-8B2026.02 | 49.78 | |
| CounterDistillTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-8B2026.02 | 49.61 | |
| LionTeacher LLM=OpenAI o1, Student Model (SLM)=Q-3B2026.02 | 49.28 | |
| IOATeacher LLM=OpenAI o1, Student Model (SLM)=L-3B2026.02 | 49.28 | |
| LaMiniTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-3B2026.02 | 49.27 | |
| CasCoDTeacher LLM=OpenAI o1, Student Model (SLM)=L-8B2026.02 | 49.01 | |
| LionTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-8B2026.02 | 48.93 | |
| Self-InstructTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-3B2026.02 | 48.46 | |
| DSSTeacher LLM=OpenAI o1, Student Model (SLM)=L-8B2026.02 | 48.42 | |
| CounterDistillTeacher LLM=OpenAI o1, Student Model (SLM)=L-8B2026.02 | 48.16 | |
| LaMiniTeacher LLM=OpenAI o1, Student Model (SLM)=Q-3B2026.02 | 48.15 | |
| UndistilledTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-14B2026.02 | 47.88 | |
| MADATeacher LLM=DeepSeek-R1, Student Model (SLM)=L-3B2026.02 | 47.76 | |
| LaMiniTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-8B2026.02 | 47.72 | |
| LionTeacher LLM=OpenAI o1, Student Model (SLM)=L-8B2026.02 | 47.63 | |
| Self-InstructTeacher LLM=OpenAI o1, Student Model (SLM)=Q-3B2026.02 | 47.36 | |
| Star-AgentsTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-3B2026.02 | 46.92 | |
| Self-InstructTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-8B2026.02 | 46.91 | |
| UndistilledTeacher LLM=OpenAI o1, Student Model (SLM)=Q-14B2026.02 | 46.72 | |
| LaMiniTeacher LLM=OpenAI o1, Student Model (SLM)=L-8B2026.02 | 46.55 | |
| MADATeacher LLM=OpenAI o1, Student Model (SLM)=L-3B2026.02 | 46.34 | |
| UndistilledTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-7B2026.02 | 45.94 | |
| CasCoDTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-3B2026.02 | 45.94 | |
| Self-InstructTeacher LLM=OpenAI o1, Student Model (SLM)=L-8B2026.02 | 45.72 | |
| Star-AgentsTeacher LLM=OpenAI o1, Student Model (SLM)=L-3B2026.02 | 45.52 | |
| DSSTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-3B2026.02 | 45.36 | |
| CounterDistillTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-3B2026.02 | 45.18 | |
| UndistilledTeacher LLM=OpenAI o1, Student Model (SLM)=Q-7B2026.02 | 44.83 | |
| CasCoDTeacher LLM=OpenAI o1, Student Model (SLM)=L-3B2026.02 | 44.63 | |
| LionTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-3B2026.02 | 44.48 | |
| DSSTeacher LLM=OpenAI o1, Student Model (SLM)=L-3B2026.02 | 44.07 | |
| CounterDistillTeacher LLM=OpenAI o1, Student Model (SLM)=L-3B2026.02 | 43.78 | |
| LaMiniTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-3B2026.02 | 43.26 | |
| LionTeacher LLM=OpenAI o1, Student Model (SLM)=L-3B2026.02 | 43.19 | |
| Self-InstructTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-3B2026.02 | 42.43 | |
| UndistilledTeacher LLM=DeepSeek-R1, Student Model (SLM)=Q-3B2026.02 | 42.35 | |
| LaMiniTeacher LLM=OpenAI o1, Student Model (SLM)=L-3B2026.02 | 42.03 | |
| Self-InstructTeacher LLM=OpenAI o1, Student Model (SLM)=L-3B2026.02 | 41.25 | |
| UndistilledTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-8B2026.02 | 41.23 | |
| UndistilledTeacher LLM=OpenAI o1, Student Model (SLM)=Q-3B2026.02 | 41.22 | |
| UndistilledTeacher LLM=OpenAI o1, Student Model (SLM)=L-8B2026.02 | 40.08 | |
| UndistilledTeacher LLM=DeepSeek-R1, Student Model (SLM)=L-3B2026.02 | 37.69 | |
| UndistilledTeacher LLM=OpenAI o1, Student Model (SLM)=L-3B2026.02 | 36.47 |