Reward Modeling on HealthBench benchmark leaderboard · SOTA2 Research

Reward Modeling on HealthBench

61.35Communication ScoreDeepSeek-V4-Flash

Evaluation Results

Method	Links
DeepSeek-V4-Flash2026.06		61.35	56.37	55.38	61.08	60.62	57.17	56.58	58.36
Qwen3.6-35B-A3B2026.06		60.99	59.51	57.26	56.37	58.72	55.44	54.87	57.59
Qwen3.6-35B-A3B2026.06		60.46	59.51	52.82	57.42	55.79	55.09	59.32	57.2
Qwen3.6-35B-A3B2026.06		58.16	56.2	56.58	61.08	57.51	59.24	62.91	58.81
DeepSeek-V4-Flash2026.06		53.55	51.31	49.57	48.52	58.55	52.68	56.75	52.99
Qwen3-8B2026.06		52.84	54.97	53.16	52.53	56.82	53.37	56.41	54.3
Qwen3-8B2026.06		51.6	53.75	55.38	51.31	57.17	51.3	54.02	53.5