Anthropic Claude Opus 4.6
Anthropic Claude Opus 4.6 is an AI model published by Anthropic, released on 2026-02-05, for Reasoning model, and 1000K context length, requiring about 0B storage, under the 不开源 license, with a 1606.00 score on GDPval-AA.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Model basics
Open source & experience
Official resources
API details
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | Context > 200K | $10.00/ 1M | $37.50/ 1M |
| Text | Context <= 200K | $5.00/ 1M | $25.00/ 1M |
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | - | $2.50/ 1M | $12.50/ 1M |
| Type | Condition | Input | Output |
|---|---|---|---|
| Text | Context <= 200K | $30.00/ 1M | $150.00/ 1M |
| Text | Context > 200K | $60.00/ 1M | $225.00/ 1M |
| Type | TTL | Write | Read |
|---|---|---|---|
| Text | 5m | $6.25/ 1M Context <= 200K | $0.500/ 1M Context <= 200K |
| Text | 5m | $12.50/ 1M Context > 200K | $1.00/ 1M Context > 200K |
| Text | 10m | $10.00/ 1M Context <= 200K | $0.500/ 1M Context <= 200K |
| Text | 10m | $20.00/ 1M Context > 200K | $1.00/ 1M Context > 200K |
Benchmark Results
Claude Opus 4.6 currently shows benchmark results led by τ²-Bench (1 / 40, score 91.89), IF Bench (1 / 29, score 94), HumanEval (2 / 39, score 95). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.
General Knowledge
9 evaluationsCoding and Software Engineer
5 evaluationsMath and Reasoning
7 evaluationsMultimodal Understanding
2 evaluationsAgent Level Benchmark
2 evaluationsAI Agent - Tool Usage
3 evaluationsCompare with other models
- Peer modelClaude Opus 4.6 vs Gemini 3.1 Pro Preview18 benchmarks
- Earlier versionClaude Opus 4.6 vs Opus 4.517 benchmarks
- Peer modelClaude Opus 4.6 vs GPT-5.414 benchmarks
- Earlier versionClaude Opus 4.6 vs Claude Opus 412 benchmarks
- Earlier versionClaude Opus 4.6 vs Opus 4.18 benchmarks
Want a custom combination? Open the compare tool
Publisher
Model Overview
Anthropic Claude Opus 4.6 is an AI model published by Anthropic, released on 2026-02-05, for Reasoning model, and 1000K context length, requiring about 0B storage, under the 不开源 license, with a 1606.00 score on GDPval-AA.
DataLearner on WeChat
Follow DataLearner on WeChat for AI model updates and research notes.
