Out-of-Domain Reasoning Aggregation on OOD Average

63.57Accuracy

Qwen3-4B-Thinking-2507 + BET

Updated 21d ago

Evaluation Results

Method
Qwen3-4B-Thinking-2507 + BET 2026.05	63.57	2,865	2.338
Qwen3-4B-Thinking-2507 + DEER 2026.05	62.41	5,434	1.224
Qwen3-4B-Thinking-2507 2026.05	62.39	6,573	1
Qwen3-4B-Thinking-2507 + DR.SAF 2026.05	61.16	3,428	1.88
Qwen3-4B-Thinking-2507 + Overthink 2026.05	60.37	6,717	0.947
Qwen3-4B-Thinking-2507 + Length-Penalty 2026.05	58.83	3,899	1.59
Qwen3-4B-Thinking-2507 + DiffAdapt 2026.05	54.2	5,547	1.03
Qwen3-4B-Thinking-2507 + VeriThinker 2026.05	52.59	4,789	1.157
Qwen3-4B-Thinking-2507 + ThinkSwitcher 2026.05	50.34	5,305	1
DeepSeek-R1-Distill-Qwen-14B 2026.05	45.5	4,949	1
DeepSeek-R1-Distill-Qwen-14B + BET 2026.05	45.43	2,308	2.141
DeepSeek-R1-Distill-Qwen-14B + DR.SAF 2026.05	44.76	3,181	1.531
DeepSeek-R1-Distill-Qwen-14B + Length-Penalty 2026.05	43.66	4,093	1.16
DeepSeek-R1-Distill-Qwen-7B 2026.05	38.73	5,540	1
DeepSeek-R1-Distill-Qwen-7B + BET 2026.05	38.33	2,299	2.385
DeepSeek-R1-Distill-Qwen-7B + DR.SAF 2026.05	38.24	3,836	1.426
DeepSeek-R1-Distill-Qwen-7B + Overthink 2026.05	36.79	5,261	1
DeepSeek-R1-Distill-Qwen-7B + Length-Penalty 2026.05	36.66	5,065	1.035
DeepSeek-R1-Distill-Qwen-7B + DEER 2026.05	35.12	4,463	1.132
DeepSeek-R1-Distill-Qwen-7B + VeriThinker 2026.05	34.55	5,001	0.988
DeepSeek-R1-Distill-Qwen-7B + DiffAdapt 2026.05	33.31	4,923	0.968
DeepSeek-R1-Distill-Qwen-7B + ThinkSwitcher 2026.05	29.99	5,050	0.85