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

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

Unified ELO 1631 ± 1, rank #333 of 1919 rated models, from 16 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
UGI - Writing58.45Writing Score91.9
AA Humanity's Last Exam39.02Accuracy (%)90.3
UGI - Natural Intelligence48.36NatInt Score89.5
AA Omniscience - Science, Engineering & Mathematics44.2Accuracy (%)85.1
AA Omniscience3.18Score84.2
AA Omniscience - Software Engineering (SWE)59Accuracy (%)83.4
AA Omniscience - Business32.3Accuracy (%)82.1
AA-Omniscience Accuracy38.97Accuracy (%)82
AA Omniscience - Humanities & Social Sciences35.9Accuracy (%)81.2
AA Long Context Reasoning76.67Accuracy (%)80.9
UGI Leaderboard45.26UGI Score80.6
AA Omniscience - Health34.1Accuracy (%)79.2

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