Long-Range Agent Loops Become a Hallmark of Top Models
ArtificialAnlys · x · 2026-07-08
Analysis by Artificial Analysis shows that models leading in long-range agent loop tasks generally run more turns. Claude Fable 5 averages about 64 turns per task at a 14.2% full pass rate, while Claude Opus 4.8, GLM-5.2, and MiniMax-M3 fall into the 56-64 turn range. Claude Sonnet 5 runs the longest, averaging about 161 turns per task, which is 2.5 times that of Fable 5.
Related event: Artificial Analysis Releases Harvey Legal Agent Benchmark Results(8 posts)→
More from Models
- Sam Altman is headed to Washington to brief Congress on OpenAI’s GPT-6 line — inductionheads · 2026-07-22
- Benchmark chart pits GPT-5.6 Luna, Grok 4.5 and Gemini 3.6 Flash on price and scores — iruletheworldmo · 2026-07-22
- Claim says Kimi was distilled from Fable, sparking a model-attribution jab — cephaloform · 2026-07-22
- Gemini 3.6 Flash is now available in Antigravity and chat — MartianOnJupiter · 2026-07-22
- Gary Marcus says LLM math skills are like knowing only a car’s engine size — GaryMarcus · 2026-07-22
- OpenAI’s Codex + GPT-5.6 Sol hits 99% recall in Project APE verification tests — soumitrashukla9 · 2026-07-22