Claude Sonnet 4.5 (High) — benchmark results

Claude Sonnet 4.5 evaluated at the high reasoning-effort setting. Provider: Anthropic. Released 2025-09-29. Access: API.

Unified ELO 1973 ± 34, rank #35 of 1776 rated models, from 27 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
CLEM Clemscore90.1Clemscore (%)100
CLEM Hot Air Balloon95.53Game Clemscore (%)100
CLEM Wordle with Clue82.5Game Clemscore (%)100
CLEM Wordle with Critic86.11Game Clemscore (%)100
HAL GAIA Level 274.42Accuracy (%)100
HAL SWE-bench Verified Mini72Score (%)100
CLEM TextMapWorld87.53Game Clemscore (%)96.7
CLEM Codenames73.85Game Clemscore (%)96.6
CLEM AdventureGame97.5Game Clemscore (%)95
CLEM MatchIt ASCII100Game Clemscore (%)94.8
HAL GAIA70.91Accuracy (%)93.8
HAL GAIA Level 177.36Accuracy (%)93.8

Interactive version: theaggregate.ai/model?slug=claude-sonnet-4-5-high · How the rankings work · Data refreshed daily, snapshot 2026-07-22.