Tutorials, deep dives and product notes — built for developers.
GPT-6 Luna vs GPT-5.4 Mini compared: rate card, context windows, knowledge cutoffs, and the shared Artificial Analysis harness where Luna leads the Intelligence Index 37 to 24 at 6.4x lower cost per task, while mini wins on speed. Vendor scorecard gaps stated honestly.
OpenAI's cheapest tier cut its price 61%, cut its hallucination rate from 93% to 77%, and lost a point on the independent index. Same-harness data on both generations, where Luna regressed, where it improved, and the ten-week price collapse.
OpenAI shipped GPT-6 Sol 90 minutes after Claude Opus 5.5, at half the token price. Artificial Analysis ran both on the same tests: Sol is cheaper to any index score up to about 44, then runs out of headroom. Every benchmark, both effort ladders and the real bill.
Terminal-Bench 4.0 checked Oct 6, 2026: Claude Opus 5.5 (64.8%) and Sonnet 5.5 (61.8%) now top the public tbench.ai board, with GPT-6 Astra and GPT-6.1 Sol tied at 58.2%. Vendor runs and Artificial Analysis results are reported separately, with harness, tokens and cost per row.
FrontierCode 1.1 Main: Opus 5.5 leads at 54.6%; new Cognition entries GPT-6.1 Sol (50.2%) and Claude Haiku 5.5 (46.4%) include effort, rollout spend, API rates and token details. Updated October 9, 2026.
DeepSWE v1.1: Datacurve's standardized leaderboard is kept separate from provider runs. Adds Google-reported Gemini 4 Argon at 77.9% and Ornith-1.5-397B at 56.0%; per-task costs are marked unavailable. Updated October 9, 2026.