Tutorials, deep dives and product notes — built for developers.
Terminal-Bench 4.0: the tbench.ai public board remains led by Claude Opus 5.5 (64.8%). Adds Kimi K3.1 Pro (65.7%, Moonshot), Gemini 4 Carbon (64%, Artificial Analysis), GPT-6.1 Terra (50.3%) and MiniMax M3.1 Flash (38.1%) as separately labeled runs. Updated Oct 30, 2026.
Interactive Terminal-Bench 3.0 leaderboard with Claude Opus 5 at 42.7%, GPT-5.6 Sol at 34.6%, GLM 5.3 at 28.3%, and all tracked frontier agent models ranked. Updated August 2026.
Claude Fable 5 leads every benchmark (80.3% Pro, 88.0% Terminal-Bench, ~87% Multi). Now the undisputed #1 for Go coding across all workflows. Updated June 9, 2026.
Claude Fable 5 leads every benchmark (80.3% Pro, 88.0% Terminal-Bench, ~87% Multi). Now the undisputed #1 for all Rust workflows. Updated June 9, 2026.
Terminal-Bench 2.1: adds Cognition's provider-reported SWE-2 Flash (89.2%) and Meta's Muse Spark Open (76.4%), labeled separately from tbench.ai public rankings. DeepSeek V4.1 Flash remains the public-board leader at 90.6%. Updated Nov 6, 2026.