Google DeepMind's Gemini 2.5 Crushes Every Benchmark—But Does It Matter?

The new model tops GPT-5 on 14 out of 15 benchmarks. Researchers say benchmarks are broken anyway.

---

Related Reading

- Google DeepMind Just Open-Sourced Gemma 3: What It Means for the AI Race - Google's Gemini Ultra 2.0 Now Powers Every Google Product - GPT-5 Beats Human Experts on Every Major Benchmark. OpenAI Says We're Not Ready for GPT-6. - OpenAI Just Dropped GPT-5 Turbo at Half the Price. The API War Is On. - Google Announces Gemini 3. Here's What Actually Matters.