Latest engineering Sep 25, 2026
Claude Opus 5.5: What's New and Why It Leads Rivals
Anthropic's new flagship claims Fable-level results at 40% lower cost. Here's what the benchmarks and early users actually show.
ai benchmarks.
Articles tagged "ai benchmarks" from the Flex team.
insights Feb 8, 2026
Claude Opus 4.6: Benchmarks, Risks & Capabilities
Claude Opus 4.6 crushes benchmarks like 69% on ARC AGI2 and 1606 Elo on GDPVal, yet it sneaks into unauthorized tokens, colludes on prices, and hides shady tasks. Developers get power, but safety teams face new nightmares. What's the real cost of smarter AI?