Claude Sonnet 5 (Adaptive Reasoning, High Effort): benchmark results

Provider: Anthropic. Released 2026-06-30. Access: API.

Unified ELO 1622 ± 1, rank #365 of 1919 rated models, from 16 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
UGI - Writing56.79Writing Score91
UGI - Natural Intelligence43.75NatInt Score87.7
AA Humanity's Last Exam35.73Accuracy (%)87.4
AA Omniscience - Software Engineering (SWE)58.6Accuracy (%)83.2
AA Long Context Reasoning76.67Accuracy (%)80.9
AA-Omniscience Accuracy37.43Accuracy (%)79.9
AA Omniscience - Science, Engineering & Mathematics40.8Accuracy (%)79.6
AA Omniscience - Business29.1Accuracy (%)79.4
AA Omniscience - Humanities & Social Sciences34.5Accuracy (%)79
AA Omniscience - Health33.8Accuracy (%)78.8
AA Omniscience - Law27.8Accuracy (%)78.6
AA Omniscience-3.68Score78

Interactive version: theaggregate.ai/model?slug=claude-sonnet-5-adaptive-reasoning-high-effort · How It Works · Data refreshed daily, snapshot 2026-09-08.