Claude Opus 5.5 benchmarked: intelligence 58, per-task cost spans 11x across five tiers
ArtificialAnlys · x · 2026-09-23
Artificial Analysis published its full evaluation of the Claude Opus 5.5 family, which ships five adaptive-reasoning tiers:
- Intelligence: Max Effort tops out at 58 on the Intelligence Index (xhigh 56, high 54, medium 51, low 42).
- Speed: the high-effort tier is fastest at 90 t/s; low effort has the lowest latency at 9.28s to first token.
- Cost: $0.55 per Intelligence Index task at low effort up to $5.98 at max — an 11x spread.
- Specs: text+image input, 1M token context (1500 A4 pages).
More from Models
- Claude Opus 5.5 and GPT-6 Sol/Luna land overnight as OpenAI cuts prices in half — AlchainHust · 2026-09-23
- Claude Opus 5.5 called the best model yet for visual design — repligate · 2026-09-23
- MachgenAI Offers Free Minimax H3 Turbo Generations for Accounts With $25+ Balance — TheMoonMidas · 2026-09-23
- Researcher: People Who Flex AI Sycophancy Screenshots Tend to Treat Humans Badly — repligate · 2026-09-23
- On Opus 5.5: The Corpus Is Full of Summaries of Summaries; Primary Experience Is Scarce — mimi10v3 · 2026-09-23
- Claude Opus 5.5 hits #2 on FrontierSWE at 62.3%, trailing GPT-6 Astra's 65.5% — scaling01 · 2026-09-23