Rails benchmark: Grok 4.6 hits 84% accuracy near Opus at 60% lower cost

AccBalanced · x · 2026-08-19

dhh shared the Rails coding benchmark results, marveling at how fast Grok is closing on the frontier and asking "what happened to Google?"

Of the 4 new models benchmarked, Grok 4.6 performed best: 4th in accuracy at 84% (vs. current best Claude Opus 5 at 92%) while costing 60% less; it also scored 33.3% recall on Rails APIs, third on the leaderboard. Claude Opus 4.8 ranked second for speed at 3m36s, just 7 seconds behind the fastest (Luna). Gemini Flash 3.7 performed mid-to-low across the board but remains one of the cheaper options.

Original post →

More from Models

Models channel →