Claude Fable 5.2 takes #1 on LiveBench with 84.9, beating GPT-6 Astra at lower cost
bindureddy · x · 2026-11-10
Bindu Reddy announces Claude Fable 5.2 has taken the #1 spot on LiveBench with an overall score of 84.9, edging out GPT-6 Astra (84.5) at a lower cost per 1M tokens. The leaderboard shows strong agentic (82.9) and design (85.1) scores, with particular strength in long agentic loops. The model is available today on ChatLLM and in Max mode.
Related event: Claude Fable 5.2 Tops LiveBench but Cost Concerns Emerge(3 posts)→
More from Models
- Early Tester: Fable 5.2 Built a 3,100-City Water Map in One Go, but Still Makes Silly Errors — alliekmiller · 2026-11-10
- Fable 5.2 burns so many tokens its 20% price cut is effectively a wash — addyosmani · 2026-11-10
- Opus formalizes CPython in 613K lines of Lean — and finds real Python bugs — pbaylies · 2026-11-10
- CursorBench 4.0: Fable 5.2 High effort hits 56.9% at $9.70 per task — SEO · 2026-11-10
- Rule of thumb: use Opus 5.5 for tasks you know, Fable 5.2 for creative exploration — EricBuess · 2026-11-10
- Claude Fable 5.2 tops FrontierSWE at 69.9%, beating GPT-6 Astra and Opus 5.5 at 1/6 the cost — aryaman2020 · 2026-11-10