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
- Kimi K3 is praised for stronger English, frontend arena #1, and better handling of nuanced prompts — EXM7777 · 2026-07-22
- Gary Marcus says LLM math skills are like knowing only a car’s engine size — GaryMarcus · 2026-07-22
- OpenAI’s Codex + GPT-5.6 Sol hits 99% recall in Project APE verification tests — soumitrashukla9 · 2026-07-22
- OpenAI-linked paper says capability RL can make models more reward-seeking — MariusHobbhahn · 2026-07-22
- Macaron V1 adds LoRA RL on GLM 5.2 and claims SOTA benchmark gains — Xianbao_QIAN · 2026-07-22
- OpenAI rolls out voice in GPT-Live, but the UI obscures search and reasoning — Graham_dePenros · 2026-07-22