Claude Sonnet 5 (xHigh) — benchmark results

Claude Sonnet 5 evaluated at the xhigh reasoning-effort setting. Provider: Anthropic. Released 2026-06-30. Access: API.

Unified ELO 1908 ± 39, rank #57 of 1776 rated models, from 8 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
OTIS Mock AIME 2024-2594.72Accuracy (%)87.2
Epoch AI - ECI153.2ECI Score80
VoxelBench1619Rating78.7
Chess Puzzles (Epoch AI)35Accuracy (%)67.9
LLM2014 Logic 2026-0743.14Median Score62.5
CursorBench 3.158.7Score (%)54.1
Epoch AI - Cursorbench58.4Score50
SimpleQA Verified25Accuracy (%)20.3

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