Anthropic

Claude Opus 4

Multimodal
Zero-eval
#2MMMU (validation)
#2ARC-AGI v2
#3MMMLU
+1 more

by Anthropic

+
+
+
+
About

Claude Opus 4 was developed as the flagship model in the Claude 4 generation, designed to push the boundaries of AI capability in complex reasoning, analysis, and multi-step problem-solving. Built to handle the most demanding enterprise tasks, it represents Anthropic's highest tier of intelligence and capability.

+
+
+
+
Pricing Range
Input (per 1M)$15.00 -$15.00
Output (per 1M)$75.00 -$75.00
Providers4
+
+
+
+
Timeline
AnnouncedMay 22, 2025
ReleasedMay 22, 2025
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown

Overall Performance

9 benchmarks
Average Score
64.6%
Best Score
88.8%
High Performers (80%+)
2

Performance Metrics

Max Context Window
328.0K
Avg Throughput
76.0 tok/s
Avg Latency
0ms
+
+
+
+
All Benchmark Results for Claude Opus 4
Complete list of benchmark scores with detailed information
MMMLU
text
0.89
88.8%
Self-reported
TAU-bench Retail
text
0.81
81.4%
Self-reported
GPQA
text
0.80
79.6%
Self-reported
MMMU (validation)
multimodal
0.77
76.5%
Self-reported
AIME 2025
text
0.76
75.5%
Self-reported
SWE-Bench Verified
text
0.72
72.5%
Self-reported
TAU-bench Airline
text
0.60
59.6%
Self-reported
Terminal-Bench
text
0.39
39.2%
Self-reported
ARC-AGI v2
multimodal
0.09
8.6%
Unverified
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+