Proximal Says Fable 5.1 Leads FrontierSWE v2

Proximal posted that Fable 5.1 is the strongest model on FrontierSWE v2, an unreleased benchmark. The post lists a score of 0.57 for Fable 5.1, ahead of Opus 5 at 0.52, Fable 5 at 0.48, and GPT-5.6 Sol at 0.32. Proximal describes the benchmark as covering complex software engineering tasks and states that FrontierSWE v2 will be released this week. The claim appears only in the company's own post. No independent confirmation or additional details about the tasks or scoring method are present in the packet.