Skip to content

Claude Opus 4.5 (32k thinking)

ModelActive
by Anthropic · family “claude-opusk-thinking”
Epoch Capabilities Index
Not scored by Epoch AI
Released
24 Nov 2025
Context window
Unknown
Max output
Unknown
Input $ / 1M tokens
Unknown
Output $ / 1M tokens
Unknown
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source

Benchmark results (10)

BenchmarkDomainScorevs best recordedSettingRunSource
FrontierMath-Tiers-1-3-v2-Privatemath34.4% ±2.8
37%
32K11 Jun 2026Eval log ↗
FrontierMath-Tier-4-v2-Privatemath4.9% ±3.4
5%
32K11 Jun 2026Eval log ↗
Chess Puzzlesgames12.0% ±3.3
17%
32K8 Dec 2025Eval log ↗
SimpleQA Verifiedknowledge45.7% ±1.6
60%
32K27 Aug 2026Eval log ↗
FrontierMath-Tier-4-2025-07-01-Privatesupersededmath4.2% ±2.9
9%
32K25 Nov 2025Epoch ↗
FrontierMath-2025-02-28-Privatesupersededmath20.7% ±2.4
39%
32K25 Nov 2025Epoch ↗
VPCTmultimodal40.0%
44%
32K—External ↗
OTIS Mock AIME 2024-2025math86.1% ±4.3
86%
32K24 Nov 2025Eval log ↗
GPQA diamondscience86.0% ±2.1
90%
32K24 Nov 2025Eval log ↗
ARC-AGIreasoning75.8%
77%
32K—External ↗

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens
This model has no public API price listing

0 recorded prices on — (OpenRouter listing); re-read on every data refresh, most recently 10h ago. Steps show when the price changed.

Events