Dev calls GPT 6.1 'painfully unusable', says Claude is 7x faster in his tests
karmay007 · x · 2026-10-16
A developer vented that OpenAI's 6.1 is "painfully unusable" — slower than a turtle, paired with a buggy Codex client that often fails to receive messages on the first 3-4 tries. He says the Claude app is far better: no useless gimmicks, a smarter model, and at least 7x faster in his experience. In his view, OpenAI only led via higher usage limits and decent-enough models while Anthropic was always ahead; now cutting limits and default speed while the model lags is "the worst decision possible" — "they seem to think they can't die."
Related event: Users complain GPT-6.1 Sol is slow and buggy, switch to Claude(2 posts)→
More from Models
- Reflection launches Beam 1.0, its first open-weight model built for coding, reasoning and agentic tasks — tomaarsen · 2026-10-16
- Reflection's 501B MoE Beam hits 463 tok/s on 8x GB200 with NVFP4 at day 0 — zhyncs42 · 2026-10-16
- JevBench v1.7.46 leaderboard: new d1-ultra tops 32 API systems at 76.1 composite — airesearch12 · 2026-10-16
- LMArena launches Agent Arena and Code Arena leaderboards for model comparison — arena · 2026-10-16
- Third-party tests find NVIDIA Nemotron-3.5 Bolt underperforms nano on pandas/numpy and decision-making tasks — norenEnmotalen · 2026-10-16
- Reflection open-sources Beam under Apache 2.0 with 40+ partner ecosystem — bhutanisanyam1 · 2026-10-16