SOTA Medical Reasoning on MedCaseReasoning (test) and PapersWithCode

72.5Accuracy

GPT-5-mini

Updated 16d ago

Evaluation Results

Method
GPT-5-mini 2025.11	72.5	-	-	-
GPT-5-mini + Verbalized Conf. 2025.11	72	73.7	0.192	0.12
GPT-5-mini + Verbalized Top-k 2025.11	70.2	70.2	0.195	0.084
GPT-5-mini + Verbalized Probability Distribution 2025.11	69.1	72.3	0.196	0.103
GPT-4.1 + Verbalized Conf. 2025.11	66.5	62.9	0.284	0.263
GPT-4.1 + Verbalized Distrib. 2025.11	65.5	66.3	0.211	0.03
GPT-4.1 2025.11	64.4	-	-	-
GPT-4.1 + Verbalized Top-k 2025.11	62.3	65.4	0.248	0.165
DeepSeek-V3 + Verbalized Conf. 2025.11	57.5	67.3	0.308	0.283
DeepSeek-V3 2025.11	56.8	-	-	-
DeepSeek-V3 + Verbalized Distrib. 2025.11	55.1	68.4	0.227	0.071
DeepSeek-V3 + Verbalized Top-k 2025.11	54.3	64.4	0.292	0.242
Qwen3-30B-A3B-Instruct + Verbalized Top-k 2025.11	44.9	58.3	0.472	0.48
Qwen3-30B-A3B-Instruct + Verbalized Conf. 2025.11	44.3	58.7	0.506	0.512
Qwen3-30B-A3B-Instruct + Verbalized Distrib. 2025.11	42.9	67.3	0.289	0.252
Qwen3-30B-A3B-Instruct 2025.11	40.4	-	-	-
Qwen3-30B-A3B-Instruct + Logit 2025.11	40.4	56.7	0.381	0.338
Qwen3-30B-A3B-Instruct + p(True) 2025.11	40.4	59.5	0.561	0.563
Qwen3-4B-Thinking 2025.11	31.7	-	-	-
Qwen3-4B-Instruct + Verbalized Conf. 2025.11	31.5	64.7	0.585	0.612
Qwen3-4B-Thinking + Verbalized Conf. 2025.11	31.5	63.9	0.509	0.546
Qwen3-4B-Instruct + Verbalized Distrib. 2025.11	31.1	64.8	0.33	0.34
Qwen3-4B-Thinking + Verbalized Top-k 2025.11	30.9	65.9	0.426	0.471
Qwen3-4B-Instruct + Verbalized Top-k 2025.11	30.1	62.3	0.527	0.568
Qwen3-4B-Instruct 2025.11	29.8	-	-	-
Qwen3-4B-Instruct + Logit 2025.11	29.8	49.2	0.519	0.513
Qwen3-4B-Instruct + p(True) 2025.11	29.8	65.1	0.661	0.665
Qwen3-4B-Thinking + Verbalized Probability Distribution 2025.11	29	66.2	0.356	0.394