Astra scores 77% vs Fable 5.1's 56% on browser use, refusals blamed for gap
steipete · x · 2026-09-08
Sharing a browser-use benchmark comparison: Astra scores 77%, well ahead of Fable 5.1 at 56%. The key differentiator is that Fable "just refuses too much" — excessive task refusals drag down its completion rate. A reminder that in agentic browser tasks, willingness to act matters as much as raw capability.
Related event: Astra Tops Browser Use Benchmark at 77%(2 posts)→
More from Models
- Kimi K3.1 Pro tops MathArena open models, closing frontier gap to about 6 months — teortaxesTex · 2026-10-26
- Ruff creator Charlie Marsh: frontier models find infinite bugs in any software — charliermarsh · 2026-10-26
- Dev testing one skill across Opus 5.5 and Sol 6.1 finds instruction following 'all over the map' — lucasmeijer · 2026-10-26
- supermemory unveils learner-1, claiming continual learning for any model — julianweisser · 2026-10-26
- Anthropic says Opus 5.5 cuts cost per task by ~40% vs Opus 5 — taufiqintech · 2026-10-26
- AI search APIs ranked: top 12 within 7 points, yet prices differ nearly 7x — FinanceYF5 · 2026-10-26