Model
Model explorer

Claude Opus 4

CLOSED
Anthropic · Claude 4 family · released May 22, 2025

Opened the Claude 4 generation and took the SWE-bench Verified coding lead at launch.

ReasoningCodingVisionFunction callingTool useAgentic
1702.9
Elo · rank #89
Parameters
Undisclosed
Active params
—
Context
200K tokens
Architecture
Dense transformer, hybrid-reasoning (parameter count undisclosed)
License
Proprietary
Languages
—
API price (in/out)
$15 / $75
Modalities
text · vision
Benchmark results
Bar shows position within the tracked field; marker = field best
Aider PolyglotCoding72.0%#11
best: Claude Opus 4.5 · 89.4%
AIMEMath75.5%#90
best: GPT-5.2 · 100.0%
GAIAAgents30.3%#9
best: MiniMax-M2 · 75.7%
GPQA DiamondReasoning79.6%#83
best: GPT-5.6 · 94.6%
Humanity's Last ExamReasoning6.7%#107
best: Claude Sonnet 5 · 57.4%
LiveCodeBenchCoding62.6%#94
best: DeepSeek-V4-Pro (Think Max) · 93.5%
MMLU-ProKnowledge86.2%#20
best: Claude Fable 5 · 91.5%
MMLUKnowledge88.8%#17
best: OpenAI o3 · 92.9%
MMMUVision76.5%#32
best: Claude Fable 5 · 89.3%
SWE-bench VerifiedCoding72.5%#52
best: Claude Fable 5 · 95.0%
tau-benchAgents81.4%#2
best: Claude Opus 4.1 · 82.4%
Terminal-BenchCoding43.2%#5
best: Claude Opus 4.5 (High) · 59.3%
Run it locally
Closed weights — available via API only. No local deployment.
Input / M tok
$15
Output / M tok
$75
Claude 4 family
Elo progression across releases
Claude Opus 4May 20251702.9Claude Sonnet 4May 20251594.8Claude Opus 4.1Aug 20251760.6Claude Sonnet 4.5Sep 20251976.7Claude Haiku 4.5Oct 20251590.8Claude Opus 4.5Nov 20252274.5Claude Opus 4.5 (High)Nov 20252301.0Claude Opus 4.5 (Medium)Nov 20252283.3Claude Opus 4.6Feb 20262459.4Claude Sonnet 4.6Feb 20262437.8Claude Opus 4.7Apr 20262702.0Claude Opus 4.8May 20262794.3
Resources
DOCSplatform.claude.com
API price $15/$75 · each benchmark row carries its own source badge (see methodology)