Claude Opus 4.5 (Thinking 32K): benchmark results

Provider: Anthropic. Released 2025-11-24. Access: API.

Unified ELO 1694 ± 1, rank #159 of 3078 rated models, from 13 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Korean CSAT 2026 (Easy Mode) - Korean100Points (out of 100)92.5
Korean CSAT 2026 (Easy Mode) - Mathematics100Points (out of 100)88.4
Korean CSAT 2026 (Easy Mode) - Life Science I48Points (out of 50)80.3
Korean CSAT 2026 (Easy Mode) - Total429.5Points (out of 450)76.2
Korean CSAT 2026 (Easy Mode) - English97Points (out of 100)66
Korean CSAT 2026 (Easy Mode) - Chemistry I45Points (out of 50)63.3
FrontierMath - Tiers 1-320.69Accuracy (%, 290 problems)61.1
Korean CSAT 2026 (Easy Mode) - Physics I33Points (out of 50)59.2
ARC-AGI-175.83Accuracy (%)57.3
Korean CSAT 2026 (Easy Mode) - Society and Culture39Points (out of 50)55.8
FrontierMath - Tiers 1-3 (v2)34.39Accuracy (%, 285 private v2 problems)53.1
FrontierMath - Tier 44.17Accuracy (%, 48 problems)44.4

Interactive version: theaggregate.ai/model?slug=claude-opus-4-5-thinking-32k · How It Works · Data refreshed daily, snapshot 2026-09-19.