LLM Evaluation & Leaderboards
News on LLM evaluation and benchmarks, covering new tests, methodology changes, leaderboard results, and whether findings can be reproduced.
Explore how researchers and engineering teams test language models before and after deployment. Coverage looks at benchmark design, meaningful comparisons, leaderboard changes, and which results teams can reproduce.
Latest coverage
Articles
NewsFable 5 tops Cursor's CursorBench 3.1 coding-agent leaderboard as the vendor eval resurfaces
NewsArena AI leaderboard hits $100 million revenue run rate eight months after launch
NewsZ.ai's open-weight GLM-5.2 matches Claude Opus 4.8 on cybersecurity benchmarks at lower cost
NewsSakana AI's Fugu Ultra claims top SWE-Bench Pro score, but testers report a real-world gap
NewsOpenAI introduces Deployment Simulation to predict model behavior before launch
- News
A new benchmark backed by Mercor shows AI agents struggle with real workplace tasks
NewsThe newly released ARC-AGI-2 brings new challenges for "reasoning" models
- News
Researchers looking for benchmarks relevant to average AI users turn to the NPR Sunday Puzzle
- News
AlphaGeometry2 has surpassed IMO gold medalist performance in geometry problems
NewsGoogle is reportedly testing Gemini against Anthropic's Claude
NewsPrimate Labs revamps its machine learning benchmark to introduce Geekbench AI 1.0
NewsGalileo's LLM Hallucination Index crowned Claude 3.5 Sonnet as the best LLM for RAG