Gemini 3.5 Pro Benchmarks Allegedly Leaked
daniel_mac8 · x · 2026-07-13
A cited post claims Gemini 3.5 Pro benchmark results have leaked, suggesting it might outperform Claude Fable 5 and GPT-5.6 in internal evaluations.
The post also mentions:
- Significant zero-shot improvements over Gemini 3.1 Pro
- Currently in private verification and testing
- Expected to launch on July 17
It's worth noting that this is an unconfirmed rumor, but if accurate, Google might not just catch up but take the outright lead.
More from Models
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- awesome-llm-leaderboards: an open-source directory of LLM leaderboards, pricing tables, comparison tools — Last_Establishment_1 · 2026-09-11
- Anthropic claims it works to keep eval environments unidentifiable to models — MaxKannen · 2026-09-11
- Nex N2.5 Pro released on Hugging Face with 407GB of weights — jinnyjuice · 2026-09-11
- RoMa v2 image matching model unveiled in the usual black poster — ducha_aiki · 2026-09-11
- OpenAI rated Astra 'Critical' for cyber capabilities — and admits it's harder to monitor — theguywhobuilds · 2026-09-11