{"object":"model_scores","generated_at":"2026-10-08T04:16:25.300Z","methodology":"https://anymodl.com/how-we-test.html","count":7,"models":[{"model_id":"~deepseek/deepseek-flash-latest","maker":"DeepSeek","lane":"tools","pass_rate":100,"p50_ms":4161,"p90_ms":11520,"tool_call_pass_rate":100,"cost_per_1k_passed_usd":1.2517,"samples":34,"nights":2,"tested_at":"2026-10-08","source":"dev1-eval"},{"model_id":"deepseek/deepseek-v4-pro","maker":"DeepSeek","lane":"tools","pass_rate":100,"p50_ms":6794,"p90_ms":17086,"tool_call_pass_rate":100,"cost_per_1k_passed_usd":5.2777,"samples":33,"nights":2,"tested_at":"2026-10-08","source":"dev1-eval"},{"model_id":"~deepseek/deepseek-flash-latest","maker":"DeepSeek","lane":"chat","pass_rate":96.4,"p50_ms":2014,"p90_ms":8442,"cost_per_1k_passed_usd":0.3489,"samples":28,"nights":2,"tested_at":"2026-10-08","source":"dev1-eval"},{"model_id":"deepseek-ai/DeepSeek-V4.1-Flash","maker":"DeepSeek","lane":"chat","pass_rate":92.9,"p50_ms":830,"p90_ms":1801,"cost_per_1k_passed_usd":0.6405,"samples":28,"nights":2,"tested_at":"2026-10-08","source":"dev1-eval"},{"model_id":"deepseek/deepseek-v4-pro","maker":"DeepSeek","lane":"agent","pass_rate":100,"p50_ms":5811,"p90_ms":12783,"tool_call_pass_rate":100,"chat_pass":100,"agent_pass":100,"cost_per_1k_passed_usd":8.2986,"samples":6,"nights":1,"tested_at":"2026-10-08","source":"agent-harness"},{"model_id":"deepseek/deepseek-v4-flash","maker":"DeepSeek","lane":"agent","pass_rate":83.3,"p50_ms":2987,"p90_ms":3024,"tool_call_pass_rate":100,"chat_pass":66.7,"agent_pass":100,"cost_per_1k_passed_usd":0.5327,"samples":6,"nights":1,"tested_at":"2026-10-08","source":"agent-harness"},{"model_id":"deepseek/deepseek-chat","maker":"DeepSeek","lane":"agent","pass_rate":100,"p50_ms":2187,"p90_ms":3160,"tool_call_pass_rate":100,"chat_pass":100,"agent_pass":100,"cost_per_1k_passed_usd":2.0045,"samples":6,"nights":1,"tested_at":"2026-10-08","source":"agent-harness"}],"stale":false}