← Back to all models
C

Claude Opus 4.5

by Anthropic
Flagship Paid API Multimodal 🏆 Ranked #11 of 85
87.8
Overall Score
out of 100
About

Anthropic's multimodal Opus model offering seamless vision-language interactions with a 200K context window. Designed for the most demanding tasks requiring deep analysis and image comprehension.

Key Metrics
Context Window
200K
tokens
Avg Response
950
milliseconds
Input Cost
$15.0
per million tokens
Output Cost
$75.0
per million tokens
Arena ELO
1345
Chatbot Arena rating
MT-Bench
9.3
out of 10
Benchmark Scores
MMLU
91.5%
HumanEval
91.5%
MATH
89.0%
GPQA
73.0%
MT-Bench
93.0/10
Capability Profile
Strengths & Limitations
Strengths
✓ Multimodal vision ✓ Long context ✓ Top-tier reasoning ✓ Safe ✓ Strong writing
Limitations
⚠ Very high cost ⚠ Slower response ⚠ Over-capable for routine tasks
Ideal Use Cases
Vision analysis Complex reasoning Scientific research Document review Multimodal workflows
Model Details
Provider Anthropic
Released 2025-05-01
Type Paid API
Multimodal Yes
Tier Flagship
Global rank #11 / 85
Pricing (USD)
Input tokens $15.0/M
Output tokens $75.0/M
Per 1,000 tokens ≈ $0.0150 input / $0.0750 output
All Benchmarks
MMLU 91.5%
HumanEval 91.5%
MATH 89.0%
GPQA 73.0%
MT-Bench 9.3/10
Arena ELO 1345
Compare this model View Rankings

You might also consider