ai benchmarks
-
Gemini 2.5 Pro leads in context and video understanding
Gemini 2.5 Pro dominates long context and video understanding tasks, scoring 92.3% on MMLU. While it excels in multimodal reasoning and math,…
Trending Now
- The collapse of Disney’s OpenAI deal and the rise of Kling AI
- The people shaping Perplexity’s $3B AI search startup
- Adept AI shifts to enterprise workflows after Amazon hires leadership
- Replicate model hosting and serverless GPU pricing analysis
- The Scale AI pivot from data labeling to defense infrastructure