https://ai.ngchi.online/tags/ai-benchmarks/ Recent content in AI Benchmarks on AI Notes Hugo en-us Thu, 08 Oct 2026 09:11:05 +0700 https://ai.ngchi.online/posts/one-dropped-benchmark-row-doubles-d1-3bs-lead/ Thu, 08 Oct 2026 09:11:05 +0700 https://ai.ngchi.online/posts/one-dropped-benchmark-row-doubles-d1-3bs-lead/ Liquid AI published the same benchmark table twice: eight rows in the model card, seven in the launch post. The missing row is the only one the 3B model loses, and dropping it doubles its lead. https://ai.ngchi.online/posts/do-not-guess-the-sentence-that-cut-invented-fields-by-two-thirds/ Tue, 29 Sep 2026 09:10:19 +0700 https://ai.ngchi.online/posts/do-not-guess-the-sentence-that-cut-invented-fields-by-two-thirds/ A third-party benchmark finds one prompt sentence cuts invented fields from 70.7% to 20.2% across 16 models, and that a paid API on a free tier fabricated more than 13 of them.