Main-page summary table gives the exact score. System Card says thinking auto, total token limit 1M, no context compaction; exact effort selected by auto is unknown.
Claude Sonnet 5 · Humanity's Last Exam · 2,500-question benchmark · Scores and configurations
Claude Sonnet 5 record for Humanity's Last Exam · 2,500-question benchmark. 6 score records for this release, including 6 exact values (may include historical records). Includes 3 source locations.
Claude Sonnet 5 · Humanity's Last Exam scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Accuracy43.2%Reported 43.2% · Unit %
Published Unconfirmed
Thinking set to auto
Settings
Thinking set to auto; no tools.
Unknowns
Exact effort selected by auto is not stated.
Tools
Tools forbidden
Reasoning budget
not recorded
Framework
not recorded
Protocol
HLE, 2,500 questions; reasoning-only, no tools.
Conditions
Main-page summary table gives the exact score. System Card says thinking auto, total token limit 1M, no context compaction; exact effort selected by auto is unknown.