Grok 4.5 Performs Worse via API
teortaxesTex · x · 2026-07-17
The author observed that Grok 4.5 appears "dumber" in the minimal API on openrouter compared to Grok Build, even failing to answer the same test anecdote correctly.
They feel its performance is on par with DSV4, or perhaps even worse; at least V4 could "guess the actual punchline," whereas the 4.5 API version completely missed it.
More from Models
- Local beats cloud: Qwen 3.8 FN handles private student data as well as frontier models — dr_lm · 2026-10-27
- Aidan Gomez: model's CoT said no tool calls right before making them — aidangomez · 2026-10-27
- Nat Lambert: Cohere's model is narrow RL training on internal infra ill-suited for open weights — natolambert · 2026-10-27
- OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
- Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27
- ChatGPT's crawler sample code strips out all Schema markup — VeryWellVersed · 2026-10-27