Anthropic
Claude Opus 5 (Adaptive Reasoning, Max Effort)
Quality Score78.5
Value Score48.0
Reliability68.5
Cache Discount90%
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image
- Output modalities
- text
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $5.00
- Output
- $25.00
- Cached Input
- $0.500
- Cached Output
- $6.25
- Cost per task
- $2.34
Capability
- Intelligence
- 63.1
- Coding
- 78.0
- Agentic
- 59.2
- Omniscience
- 37.1
- Correct
- 60.9%
- Blended price
- $3.85
Answer outcomes
Correct 60.9%Incorrect 23.8%Abstained 15.3%
Artificial Analysis benchmarks
- GDPval-AA v2
- 67%
- τ³-Banking
- 42%
- Terminal-Bench v2.1
- 89%
- SciCode
- 56%
- Humanity’s Last Exam
- 55%
- GPQA Diamond
- 93%
- CritPt
- 29%
- AA-Omniscience
- 69%
- AA-LCR
- 76%
Similar models
- Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)AnthropicQuality Score 77.5Value Score 47.4
- Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)AnthropicQuality Score 79.9Value Score 45.0
- Claude Opus 5 (Adaptive Reasoning, High Effort)AnthropicQuality Score 76.2Value Score 46.7
- Claude Opus 5 (Adaptive Reasoning, Medium Effort)AnthropicQuality Score 73.1Value Score 44.7
- Claude Opus 5 (Adaptive Reasoning, Low Effort)AnthropicQuality Score 68.1Value Score 41.0
- Claude Sonnet 5 (Adaptive Reasoning, Max Effort)AnthropicQuality Score 64.1Value Score 43.6