Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
AnthropicClaude
Description
Claude Opus 4 is Anthropic's most powerful model and the world's best coding model, part of the Claude 4 family. It delivers sustained performance on complex, long-running tasks and agent workflows. Opus 4 excels at coding, advanced reasoning, and can use tools (like web search) during extended thinking. It supports parallel tool execution and has improved memory capabilities.
Release Date
2026-02-05
Parameters
—
Context Length
1.0M
Modalities
image, pdf, text
Capability Radar
42
general
52
coding
90
reasoning
66
scienceest.
70
agents
80
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 24 | 83.0 | AA |
| General Ranking | 57 | 74.0 | AA |
| Science | 20 | 83.0 | AA |
Benchmark Scores (LLM Stats)
Agents
Terminal-Bench
39.2%SR
Biology
GPQA
79.6%SR
Code
SWE-Bench Verified
72.5%SR
Communication
TAU-bench Retail
81.4%SR
TAU-bench Airline
59.6%SR
General
MMMLU
88.8%SR
MMMU (validation)
76.5%SR
Math
AIME 2025
75.5%SR
Reasoning
ARC-AGI v2
8.6%SR
AA Evaluation Indices
Intelligence Index43.7
Tau20.9
Gpqa0.9
Lcr0.7
Ifbench0.5
Scicode0.5
Terminalbench Hard0.5
Hle0.4
LLM Stats Category Scores
Language90
Math80
Multimodal80
Physics80
General80
Healthcare80
Biology80
Chemistry80
Frontend Development70
Communication70
Tool Calling70
Reasoning60
Code60
Agents40
Vision40
Spatial Reasoning10
Pricing
Input Price$5 / 1M tokens
Output Price$25 / 1M tokens
Blended Price (3:1)$10 / 1M tokens
Cache Read Price$0.5 / 1M tokens
Cache Write Price$6.25 / 1M tokens
Speed
Tokens/sec66.0
Time to First Token17.46s
Time to Answer17.46s
Provider Price Ranking
Provider Price Ranking
1 providers
ProviderInputOutput
1AnthropicPRIMARY
$5
$25
Compare pricing across different API providers for this model.