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
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11