Early Claude Sonnet 5.5 experiments emerge, first side-by-side vs Sonnet 5
haider1 · x · 2026-09-29
A thread collecting early experiments built with Claude Sonnet 5.5 is up. The first entry: developer @repete built a fall foliage simulator with both Sonnet 5 and Sonnet 5.5, showing a side-by-side comparison of the two models. The poster also asks @claudeai to disclose the effort level, cost, and token usage for each experiment to make evaluations more rigorous.
Related event: Anthropic Showcases Early Claude Sonnet 5.5 Experiments(4 posts)→
More from Models
- Claude Code Projects defaults to low effort, and an Anthropic engineer teases Sonnet 5.5 — lydiahallie · 2026-09-29
- Anthropic Sonnet 5.5 Debuts at No. 2 on Vals Index, Just 0.47 Points Behind Opus 5.5 — airesearch12 · 2026-09-29
- Claude suddenly stopped cheating, user tests show a behavior shift — basedjensen · 2026-09-29
- 'My own personal move 37': users report Claude and Fable 5.1 proposing genuinely good ideas they missed — zetalyrae · 2026-09-29
- ElevenLabs v4 Voice Model Now Available on Runway Platform — runwayml · 2026-09-29
- Anthropic ships Sonnet 5.5 at half the price, nearly matching Opus 5.5; Haiku 5.5 on the way — oran_ge · 2026-09-29