Will Gemini 1.5 Pro seem to be as good as Gemini 1.0 Ultra for common use cases? [Personal judgement]


Our teams continue pushing the frontiers of our latest models with safety at the core. They are making rapid progress. In fact, we’re ready to introduce the next generation: Gemini 1.5. It shows dramatic improvements across a number of dimensions and 1.5 Pro achieves comparable quality to 1.0 Ultra, while using less compute.

Once both have been publically available for long enough to get users, I'll resolve this to whether or not I think it's roughly as good as Ultra or noiceably worse for generic LLM use cases.

Get Ṁ600 play money
Sort by:
bought Ṁ40 YES

It's similar to 1.0 Ultra on most benchmarks with better safety/refusal. Inference time probably faster too? Likely to be "as good as" 1.0 Ultra