Claude Opus 5.5 tops writing benchmark at 2631 Elo, a record 307-point lead
teortaxesTex · x · 2026-09-24
Claude Opus 5.5 is the new #1 on a popular AI writing benchmark at 2631 Elo — a 307-point gap over second-place Fable (2324), the largest single jump since the leaderboard launched in June 2026. It's also the first model to clear 91/100 on the rubrics. The catch: at max effort one script takes 17 minutes and $3.43, the slowest config on the board and top-5 most expensive. Commenter teortaxes notes the model's prior writing weaknesses were always fixable — Anthropic just didn't prioritize them.
More from Models
- TeleOCR, a Qwen2.5-VL-based document parsing model, trends on Hugging Face — StarDoc-AI · 2026-09-24
- Rumor: SSI to launch its first model this month after security-related delay — iruletheworldmo · 2026-09-24
- Which sub-40B finetunes work best for mimicking a writing style? — Borkato · 2026-09-24
- First-day Opus 5.5 verdict: power user says it replaced Astra entirely — kimmonismus · 2026-09-24
- Opus 5.5 impresses early users; Mirage launch video made with just 4 turns of edits — seanwbren · 2026-09-24
- Open source multimodal decision model XOR launches on Hugging Face, 260k context, Qwen-based — TheMoonMidas · 2026-09-24