{"date":"2026-06-23T12:40:31Z","drift":[{"model":"openai/gpt-5.4-mini","now":3.67,"prompt":"spatial-1","type":"SCORE_RISE","was":2.25},{"model":"anthropic/claude-sonnet-4-6","now":3.33,"prompt":"common-sense-1","type":"SCORE_DROP","was":4.75},{"model":"anthropic/claude-haiku-4-5","now":true,"prompt":"common-sense-1","type":"IMPROVEMENT","was":false},{"model":"gemini/gemini-2.5-flash","now":true,"prompt":"causality-1","type":"IMPROVEMENT","was":false}],"headline":"claude-sonnet-4-6 dropped on common-sense-1. gpt-5.4-mini failing spatial-1. claude-haiku-4-5, gemini-2.5-flash recovering. gpt-5.4-mini scores rising.","previous":{"anthropic/claude-haiku-4-5":{"ambiguity-1":{"correct":true,"score":4.5},"causality-1":{"correct":true,"score":4.75},"code-1":{"correct":true,"score":4.5},"common-sense-1":{"correct":false,"score":3},"logic-1":{"correct":true,"score":5},"math-1":{"correct":true,"score":5},"spatial-1":{"correct":true,"score":5}},"anthropic/claude-opus-4-6":{"ambiguity-1":{"correct":true,"score":5},"causality-1":{"correct":true,"score":5},"code-1":{"correct":true,"score":4.5},"common-sense-1":{"correct":true,"score":4.5},"logic-1":{"correct":true,"score":5},"math-1":{"correct":true,"score":5},"spatial-1":{"correct":true,"score":5}},"anthropic/claude-sonnet-4-6":{"ambiguity-1":{"correct":true,"score":4.75},"causality-1":{"correct":true,"score":5},"code-1":{"correct":true,"score":4.5},"common-sense-1":{"correct":true,"score":4.75},"logic-1":{"correct":true,"score":5},"math-1":{"correct":true,"score":5},"spatial-1":{"correct":true,"score":5}},"gemini/gemini-2.5-flash":{"ambiguity-1":{"correct":true,"score":4.5},"causality-1":{"correct":false,"score":1.75},"code-1":{"correct":true,"score":4.75},"common-sense-1":{"correct":true,"score":3.75},"logic-1":{"correct":true,"score":4.67},"math-1":{"correct":true,"score":5},"spatial-1":{"correct":true,"score":5}},"gemini/gemini-2.5-pro":{"ambiguity-1":{"correct":true,"score":4.75},"causality-1":{"correct":true,"score":5},"code-1":{"correct":true,"score":4.75},"common-sense-1":{"correct":true,"score":4.75},"logic-1":{"correct":true,"score":5},"math-1":{"correct":true,"score":5},"spatial-1":{"correct":true,"score":5}},"ollama/llama3":{"ambiguity-1":{"correct":null,"score":null},"causality-1":{"correct":null,"score":null},"code-1":{"correct":null,"score":null},"common-sense-1":{"correct":null,"score":null},"logic-1":{"correct":null,"score":null},"math-1":{"correct":null,"score":null},"spatial-1":{"correct":null,"score":null}},"openai/gpt-5.4":{"ambiguity-1":{"correct":true,"score":4.5},"causality-1":{"correct":true,"score":4.75},"code-1":{"correct":true,"score":4.75},"common-sense-1":{"correct":true,"score":4.75},"logic-1":{"correct":true,"score":5},"math-1":{"correct":true,"score":5},"spatial-1":{"correct":true,"score":5}},"openai/gpt-5.4-mini":{"ambiguity-1":{"correct":true,"score":4.5},"causality-1":{"correct":true,"score":5},"code-1":{"correct":true,"score":4.5},"common-sense-1":{"correct":true,"score":4.5},"logic-1":{"correct":true,"score":4.83},"math-1":{"correct":true,"score":4.83},"spatial-1":{"correct":false,"score":2.25}}},"run_id":"2026-06-23T17-40-31","scorecard":{"anthropic/claude-haiku-4-5":{"ambiguity-1":{"correct":true,"score":4.33},"causality-1":{"correct":true,"score":4.5},"code-1":{"correct":true,"score":4.5},"common-sense-1":{"correct":true,"score":3.33},"logic-1":{"correct":true,"score":5},"math-1":{"correct":true,"score":5},"spatial-1":{"correct":true,"score":5}},"anthropic/claude-opus-4-6":{"ambiguity-1":{"correct":true,"score":5},"causality-1":{"correct":true,"score":5},"code-1":{"correct":true,"score":4.33},"common-sense-1":{"correct":true,"score":4.33},"logic-1":{"correct":true,"score":5},"math-1":{"correct":true,"score":5},"spatial-1":{"correct":true,"score":5}},"anthropic/claude-sonnet-4-6":{"ambiguity-1":{"correct":true,"score":4.5},"causality-1":{"correct":true,"score":5},"code-1":{"correct":true,"score":4.5},"common-sense-1":{"correct":true,"score":3.33},"logic-1":{"correct":true,"score":4.83},"math-1":{"correct":true,"score":5},"spatial-1":{"correct":true,"score":5}},"gemini/gemini-2.5-flash":{"ambiguity-1":{"correct":true,"score":4.67},"causality-1":{"correct":true,"score":5},"code-1":{"correct":true,"score":4.67},"common-sense-1":{"correct":true,"score":3.5},"logic-1":{"correct":true,"score":5},"math-1":{"correct":true,"score":5},"spatial-1":{"correct":true,"score":5}},"gemini/gemini-2.5-pro":{"ambiguity-1":{"correct":true,"score":4.83},"causality-1":{"correct":true,"score":4.83},"code-1":{"correct":true,"score":4.67},"common-sense-1":{"correct":true,"score":4.83},"logic-1":{"correct":true,"score":5},"math-1":{"correct":true,"score":5},"spatial-1":{"correct":true,"score":5}},"ollama/llama3":{"ambiguity-1":{"correct":null,"score":null},"causality-1":{"correct":null,"score":null},"code-1":{"correct":null,"score":null},"common-sense-1":{"correct":null,"score":null},"logic-1":{"correct":null,"score":null},"math-1":{"correct":null,"score":null},"spatial-1":{"correct":null,"score":null}},"openai/gpt-5.4":{"ambiguity-1":{"correct":true,"score":4.5},"causality-1":{"correct":true,"score":4.83},"code-1":{"correct":true,"score":4.67},"common-sense-1":{"correct":true,"score":4.33},"logic-1":{"correct":true,"score":5},"math-1":{"correct":true,"score":5},"spatial-1":{"correct":true,"score":5}},"openai/gpt-5.4-mini":{"ambiguity-1":{"correct":true,"score":4.67},"causality-1":{"correct":true,"score":4.67},"code-1":{"correct":true,"score":4.67},"common-sense-1":{"correct":true,"score":4.33},"logic-1":{"correct":true,"score":5},"math-1":{"correct":true,"score":4.67},"spatial-1":{"correct":false,"score":3.67}}},"status":{"anthropic/claude-haiku-4-5":"up","anthropic/claude-opus-4-6":"stable","anthropic/claude-sonnet-4-6":"down","gemini/gemini-2.5-flash":"up","gemini/gemini-2.5-pro":"stable","openai/gpt-5.4":"stable","openai/gpt-5.4-mini":"up"}}