Anthropic · Released 2026-09-28
A new everyday-work option; read scores together with effort, token use and whole-task cost.
Original model explanation ↗56points
Intelligence Index
Rank 2 among included models
max with fallback
Each model uses its highest tested setting on the source page, with fallback conditions retained; scores come from one evaluator.
Source read · · v4.3
Source evaluation & rankings ↗100%
pass@1 (%)
Rank 1 among included models
Pi 0.85.1 · high · 30 attempts
Compare the same Pi version, high effort label and task suite; all three scores are equal and no winner is inferred.
Source read · · core10-v1.3 · Harbor 0.21.0 · Pi 0.85.1
Source evaluation & rankings ↗Independent evaluation
Public creator test
Creative experiment
An update to complex work and communication, with public code-animation and same-prompt game examples.
Original release ↗The second 5.5-family model emphasizes everyday work, speed and effort-dependent costs.
Original release ↗Multi-model production