{"date":"2026-06-26T08:47:13Z","drift":[{"model":"openai/gpt-5.4","now":4,"prompt":"math-1","type":"SCORE_DROP","was":5},{"model":"anthropic/claude-sonnet-4-6","now":true,"prompt":"code-1","type":"IMPROVEMENT","was":null},{"model":"anthropic/claude-sonnet-4-6","now":true,"prompt":"ambiguity-1","type":"IMPROVEMENT","was":null},{"model":"anthropic/claude-sonnet-4-6","now":true,"prompt":"common-sense-1","type":"IMPROVEMENT","was":null},{"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":"gpt-5.4 dropped on math-1. claude-sonnet-4-6, claude-sonnet-4-6, claude-sonnet-4-6, claude-haiku-4-5, gemini-2.5-flash recovering.","previous":{"anthropic/claude-haiku-4-5":{"ambiguity-1":{"correct":true,"score":4.5},"causality-1":{"correct":true,"score":4.67},"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":4.4},"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":null,"score":null},"causality-1":{"correct":true,"score":5},"code-1":{"correct":null,"score":null},"common-sense-1":{"correct":null,"score":null},"logic-1":{"correct":true,"score":4.8},"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":2.5},"code-1":{"correct":true,"score":4.75},"common-sense-1":{"correct":true,"score":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":4.5},"causality-1":{"correct":true,"score":4.67},"code-1":{"correct":true,"score":4.75},"common-sense-1":{"correct":true,"score":5},"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":4.6},"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":4.2}},"openai/gpt-5.4-mini":{"ambiguity-1":{"correct":true,"score":4.5},"causality-1":{"correct":true,"score":4.67},"code-1":{"correct":true,"score":4.25},"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}}},"run_id":"2026-06-26T13-47-13","scorecard":{"anthropic/claude-haiku-4-5":{"ambiguity-1":{"correct":true,"score":4.17},"causality-1":{"correct":true,"score":4.83},"code-1":{"correct":true,"score":4.67},"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":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}},"anthropic/claude-sonnet-4-6":{"ambiguity-1":{"correct":true,"score":4.33},"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":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":true,"score":4.83},"code-1":{"correct":true,"score":4.67},"common-sense-1":{"correct":true,"score":4.83},"logic-1":{"correct":true,"score":4.5},"math-1":{"correct":true,"score":5},"spatial-1":{"correct":true,"score":5}},"gemini/gemini-2.5-pro":{"ambiguity-1":{"correct":true,"score":4.33},"causality-1":{"correct":true,"score":4.83},"code-1":{"correct":true,"score":4.83},"common-sense-1":{"correct":true,"score":5},"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":4.67},"code-1":{"correct":true,"score":4.67},"common-sense-1":{"correct":true,"score":4.5},"logic-1":{"correct":true,"score":5},"math-1":{"correct":true,"score":4},"spatial-1":{"correct":true,"score":4.17}},"openai/gpt-5.4-mini":{"ambiguity-1":{"correct":true,"score":4.33},"causality-1":{"correct":true,"score":4.67},"code-1":{"correct":true,"score":4.5},"common-sense-1":{"correct":true,"score":4.67},"logic-1":{"correct":true,"score":5},"math-1":{"correct":true,"score":5},"spatial-1":{"correct":true,"score":5}}},"status":{"anthropic/claude-haiku-4-5":"up","anthropic/claude-opus-4-6":"stable","anthropic/claude-sonnet-4-6":"up","gemini/gemini-2.5-flash":"up","gemini/gemini-2.5-pro":"stable","openai/gpt-5.4":"down","openai/gpt-5.4-mini":"stable"}}