Haiku 5.5 already burns more tokens at medium than Opus 5.5 does
haider1 · x · 2026-10-08
Responding to critics asking who even maxes out Haiku, the author argues you don't need to: Haiku 5.5 at medium already uses more tokens than Opus 5.5 at medium. He still keeps Opus 5.5 for heavy lifting (until it gets nerfed) and uses "6.1 sol" for almost everything else.
More from Models
- Closed frontier models lead open-weights by 3-6 months, agentic timeline shows — JosephJacks_ · 2026-10-08
- GPT-6 rolls out to Plus/Pro/Enterprise today, free users start tomorrow — michpokrass · 2026-10-08
- GPT-6's interleaved thinking answers instantly while it keeps reasoning — michpokrass · 2026-10-08
- Testing if a model is leaderboard-slop with niche 2010s cartoon trivia — BreadUndPeeTears · 2026-10-08
- Haiku 5.5 hits 122 tps on OpenRouter, nearly 2x faster than Luna — weswinder · 2026-10-08
- Claude Haiku 5.5 matches GPT-6 Luna pricing but a stingier tokenizer hides a 1.25x cost hike — Simon Willison · 2026-10-08