Claude Fable 5.2 tops FrontierCode 2.0 at 49.1, at a third of Fable 5.1's cost
nrehiew_ · x · 2026-11-10
Cognition announces Claude Fable 5.2 in Devin Desktop and Devin CLI, taking #1 on FrontierCode 2.0 with a score of 49.1. At low reasoning effort it beats its predecessor at about a third of Fable 5.1's cost. nrehiew notes only Fable models show a performance dip at max reasoning while Opus and Sonnet don't, questioning whether post-training differs that much. The chart also compares GPT-6.1 Sol, GPT-6 Astra, Gemini 4 Carbon, and Haiku 5.5 on score-vs-cost.
More from coding & agent
- 20 Python MCP Tools Worth Knowing, From Server Building to Gateways, Security and Eval — MaryamMiradi · 2026-11-10
- Prompting tip: describe the problem, not your solution, for better agent grilling — mattpocockuk · 2026-11-10
- The One-Person Million-Dollar AI Agency: An Agent-Stack Blueprint With the Math — boringmarketer · 2026-11-10
- Developer natively manages 25-30 parallel agent sessions on macOS with Rex — jonathan_wilke · 2026-11-10
- Pi Dash orchestrates 10 Muse Code agents with Muse Ember, rewriting 178K lines in a day — AIatMeta · 2026-11-10
- 125 prompt injections, zero executed: testing a propose-and-policy agent architecture — RI4D · 2026-11-10