https://policybench.org/ weekly 1 https://policybench.org/paper monthly 0.7 https://policybench.org/model/gpt-5.6-sol monthly 0.6 https://policybench.org/model/gpt-5.6-luna monthly 0.6 https://policybench.org/model/gpt-5.5 monthly 0.6 https://policybench.org/model/gpt-5.6-terra monthly 0.6 https://policybench.org/model/claude-fable-5 monthly 0.6 https://policybench.org/model/gemini-3.1-pro-preview monthly 0.6 https://policybench.org/model/claude-opus-4.7 monthly 0.6 https://policybench.org/model/grok-4.3 monthly 0.6 https://policybench.org/model/claude-sonnet-4.6 monthly 0.6 https://policybench.org/model/gemini-3-flash-preview monthly 0.6 https://policybench.org/model/gemini-3.5-flash monthly 0.6 https://policybench.org/model/grok-build-0.1 monthly 0.6 https://policybench.org/model/gemini-3.1-flash-lite-preview monthly 0.6 https://policybench.org/model/deepseek-v4-pro monthly 0.6 https://policybench.org/model/qwen-3.7-max monthly 0.6 https://policybench.org/model/glm-5.2 monthly 0.6 https://policybench.org/model/claude-opus-4.8 monthly 0.6 https://policybench.org/model/minimax-m3 monthly 0.6 https://policybench.org/model/claude-haiku-4.5 monthly 0.6 https://policybench.org/model/gpt-5.4-mini monthly 0.6 https://policybench.org/model/claude-sonnet-5 monthly 0.6 https://policybench.org/model/kimi-k2.6 monthly 0.6 https://policybench.org/model/gpt-5.4-nano monthly 0.6