Anthropic: Claude Opus 4.6
8.2 / 10
1M context
Proprietary
About this model
Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective...
Benchmark Scores
HLE
53.0
MMLU
91.05
MMMU
77.3
IFEval
94.0
MATH-500
97.6
SimpleQA
72.0
AIME-2025
99.79
HumanEval
95.0
SWE-Bench
77.83
SWE-Bench-Verified
80.84
Terminal-Bench-2.1
65.4
Technical Specs
- Architecture: text+image+file->text
- Context Window: 1,000,000 tokens
- Input Modalities: text
Hardware Requirements
- API-only (no local hardware needed)
Pricing
| Input | Output | Currency |
|---|---|---|
| 5.0 / 1M tokens | 25.0 / 1M tokens | USD |