Claude Sonnet 5 (High) — benchmark results

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

Unified ELO 1914 ± 26, rank #45 of 1726 rated models, from 14 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Chatbot Arena (Code)1551Elo94.4
Chatbot Arena (Text)1464Elo91.5
WeirdML68.78Average Score88.1
Agent Arena - Confirmed Success11.79Confirmed Success (%)85.7
Chatbot Arena (Vision)1263Arena Score84.8
Mercor APEX32.5Best Pass@1 (%)80.9
Agent Arena - Praise vs Complaint14Praise vs Complaint (%)75
Opus Magnum Bench26.55Human-normalized score (%)70.6
Agent Arena - Tool Hallucination1.11Tool Hallucination (%)67.9
Chatbot Arena (Document)1476Elo67.7
Agent Arena7.72Net Improvement (%)57.1
CursorBench 3.157Score (%)54.2

Interactive version: aibenchmarks.dev/model?slug=claude-sonnet-5-high · How the rankings work · Data refreshed daily, snapshot 2026-07-08.