New Gemini 4 Pro checkpoint lands in Arena with extended thinking
Arena quietly added a new Gemini 4 Pro checkpoint with extended thinking; most testers find it worse than the first checkpoint, some call it an upgrade, and the author advises judging multi-run consistency rather than single generations.

new gemini 4 pro checkpoint just dropped in arena with extended thinking most testers are getting worse results than the first checkpoint some are saying it’s an upgrade from the last checkpoint feels like another internal test so If you’re testing it, focus on multi-run consistency, not a single generation and note these checkpoints won’t stay up long hopefully the final release model (rumored weeks away) wouldn’t be nerfed on day 1 like Lyra says