Atlas

Models

← All models

Claude Haiku 5.5

Anthropic · 2026-10-07

Claude Haiku 5.5 is Anthropic's October 7, 2026 model for high-volume, latency-sensitive work. It supports text and image inputs, adaptive thinking with adjustable effort, a one-million-token context window and up to 128K output tokens. Adaptive thinking defaults to medium effort. The official migration guide says it has no server-side model fallback. Its June 2026 knowledge cutoff is published only to month precision.

Benchmark scores

BenchmarkScore
A-Fantasia (Valid Attempts with Retries)72.3
A-Fantasia Chess (Valid Attempts with Retries)68.0
A-Fantasia Cube (Valid Attempts with Retries)79.0
A-Fantasia Spelling (Valid Attempts with Retries)70.0
AA-Briefcase v1.1 Elo1578
AA-LCR v1.182.7
AA-Omniscience Index10.7
Artificial Analysis Intelligence Index v4.3.243.4
Artificial Analysis Omniscience Accuracy36.4
Artificial Analysis Omniscience Hallucination Rate40.4
AutomationBench-AA 1.0.636.0
Capability162.1
CritPt (avg@5)22.6
CursorBench 4.048.4
GDP.pdf (Artificial Analysis, All-pass)20.8
GDP.pdf (Artificial Analysis, Mean Criteria)76.7
GDPval-AA v2.11620
Harvey LAB-AA89.9
Humanity's Last Exam (Text-Only)44.4
RuneBench4.5
RuneBench Skill - Attack42.0
RuneBench Skill - Cooking390
RuneBench Skill - Crafting16.0
RuneBench Skill - Defence56.0
RuneBench Skill - Firemaking240
RuneBench Skill - Fishing440
RuneBench Skill - Fletching45.0
RuneBench Skill - Hitpoints63.0
RuneBench Skill - Magic85.0
RuneBench Skill - Mining298
Loading Atlas data…