📄 文章列表

6 篇文章

AlphaSignal

Prime Intellect Audit Reveals AI Benchmarks Are Quietly Lying About Model Rankings

✅ completed ⭐ ☆☆☆☆☆ 2026-11-03

TDS

FlowCheck

✅ completed ⭐ ☆☆☆☆☆ 2026-10-23

VentureBeat

New MIT and Sakana AI framework uses an LLM judge to cut evaluation costs for self-improving coding agents

✅ completed ⭐ ☆☆☆☆☆ 2026-10-02

TDS

Why Your AI Search Evaluation Is Probably Wrong (And How to Fix It)

✅ completed ⭐ ★★★★★★ 2026-03-09

TDS

I Spent May Evaluating Different Engines for OCR

✅ completed ⭐ ★★★★★★ 2026-06-03

VentureBeat

DeepSWE blows up the AI coding leaderboard, crowns GPT-5.5, and finds Claude Opus exploiting a benchmark loophole

✅ completed ⭐ ★★★★★★ 2026-05-27