Claude Opus 4.5 (20251101) — benchmark results

November 1, 2025 Claude Opus 4.5 snapshot, tracked when sources report the dated API model. Provider: Anthropic. Released 2025-11-01. Access: API.

Unified ELO 1767 ± 10, rank #170 of 1776 rated models, from 55 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Gorilla API Bench (BFCL)77.47Overall Accuracy (%)100
Vals AI MGSM94.76Accuracy (%)98.3
AraGen80.293C3H Score (%)94
SEAL - SciPredict23.05Score92.9
Icelandic LLM - WinoGrande-IS94.67Score (%)92.3
Chatbot Arena (Text)1469Elo92.2
WebApp1K Duo76.3Pass@1 (%)90.6
Vals AI MortgageTax68.68Accuracy (%)89
EQ-Bench Creative Writing v31598.2Elo88.5
Icelandic LLM - Belebele-IS93.78Score (%)88.5
EQ-Bench Longform Writing73.1Writing Score (0-100)85.7
Icelandic LLM - GED74.5Score (%)85.7

Interactive version: theaggregate.ai/model?slug=claude-opus-4-5-20251101 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.