Claude Sonnet 5 (Adaptive Reasoning, Max Effort) — benchmark results

Claude Sonnet 5 evaluated in adaptive-reasoning mode at max effort. Provider: Anthropic. Released 2026-06-30. Access: API.

Unified ELO 1915 ± 41, rank #55 of 1776 rated models, from 37 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Artificial Analysis Intelligence Index53.35Intelligence Index98
AA Omniscience - Software Engineering (SWE) - Julia72Accuracy (%)97.1
AA GDPval1607ELO97
GDPval-AA1607Elo97
AA SciCode53.59Accuracy (%)96.8
AA GPQA Diamond91.11Accuracy (%)95.9
AA Humanity's Last Exam39.57Accuracy (%)95.9
AA Omniscience - Software Engineering (SWE) - Swift80Accuracy (%)95.9
AA-Briefcase42.32Rubric Pass Rate (%)95.7
AA Omniscience15.32Score95.1
AA CritPt16.86Accuracy (%)95
UGI - Writing62.71Writing Score94.8

Interactive version: theaggregate.ai/model?slug=claude-sonnet-5-adaptive-reasoning-max-effort · How the rankings work · Data refreshed daily, snapshot 2026-07-22.