Skip to content

Claude Opus 4

ModelActive
by Anthropic · family “claude-opus”
Epoch Capabilities Index
142.7 #94 of 268
90% CI 140.0 – 144.3
Released
22 May 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 (22)

BenchmarkDomainScorevs best recordedSettingRunSource
LMCAagents37.4%
55%
unknown—External ↗
DTBenchreasoning81.6%
82%
unknown—External ↗
FrontierMath-Tier-4-2025-07-01-Privatesupersededmath4.2% ±2.9
9%
27K1 Jul 2025Epoch ↗
DeepResearch Benchagents46.8%
85%
2K—External ↗
GSO-Benchcoding6.9%
15%
——External ↗
ARC-AGI-2reasoning8.6%
9%
16K—External ↗
METR Time Horizonsagents63.9%
75%
16K—External ↗
GeoBenchmultimodal49.0%
56%
32K—External ↗
FrontierMath-2025-02-28-Privatesupersededmath4.5% ±1.2
9%
—4 Jul 2025Epoch ↗
Fiction.LiveBenchlong-context61.1%
63%
——External ↗
Lech Mazur Writingother83.6%
97%
16K—External ↗
VPCTmultimodal38.0%
42%
16K—External ↗
HLEknowledge10.7%
20%
unknown—External ↗
WeirdMLcoding43.7% ±0.0
47%
16K—External ↗
Aider polyglotcoding72.0%
82%
32K—External ↗
OTIS Mock AIME 2024-2025math64.4% ±7.2
64%
27K28 May 2025Eval log ↗
SimpleBenchreasoning58.8%
72%
12K—External ↗
Cybenchcoding38.0%
41%
——External ↗
SWE-Bench verifiedcoding70.7% ±2.1
85%
—6 Feb 2026Eval log ↗
GPQA diamondscience76.3% ±3.0
80%
16K22 May 2025Eval log ↗
MATH level 5math85.0% ±1.0
87%
—22 May 2025Epoch ↗
ARC-AGIreasoning35.7%
36%
16K—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

No events recorded yet.