Mikhail Doroshenko

Archives
Log in
Subscribe
July 7, 2026

AI Benchmark Digest — 2026-07-07

AI Benchmark Digest — 2026-07-07

View on AI Benchmark Hub

Daily

New Benchmarks (1)

  • SkillsBench (With-skills score (%)): GPT-5.5 leads with 67.3 across 21 models. SkillsBench (BenchFlow) evaluates how effectively agentic models use modular Skills — folders of instructions, scripts, and resources — to complete tasks across diverse domains; scored by task completion with the Skills available (the benchmark also reports skill-lift, the with-minus-without-Skills gain).

New #1 Leaders (1)

  • Agent Arena - Confirmed Success (Confirmed Success (%)): minimax-m2.7 MiniMax · Modified MIT (19.55) beat Claude Fable 5 (High) (16.12) by 3.43.
Don't miss what's next. Subscribe to Mikhail Doroshenko:
← Newer AI Benchmark Digest — 2026-07-08 Older → AI Benchmark Digest — 2026-07-05
Powered by Buttondown, the easiest way to start and grow your newsletter.