Anthropic
Claude Sonnet 4.6 (Non-reasoning, Low Effort)
Quality Score44.5
Value Score28.5
Reliability49.0
Cache Discount90%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text, image
- Output modalities
- text
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $3.00
- Output
- $15.00
- Cached Input
- $0.300
- Cached Output
- $3.75
- Cost per task
- not available
Capability
- Intelligence
- 35.1
- Coding
- not available
- Agentic
- not available
- Omniscience
- -2.1
- Correct
- 36.5%
- Blended price
- $2.31
Answer outcomes
Correct 36.5%Incorrect 38.6%Abstained 24.9%
Artificial Analysis benchmarks
- SciCode
- 44%
- Humanity’s Last Exam
- 11%
- GPQA Diamond
- 80%
- CritPt
- 1%
- AA-Omniscience
- 49%
- AA-LCR
- 65%
Similar models
- Claude Sonnet 5 (Non-reasoning, High Effort)AnthropicQuality Score 51.2Value Score 34.0
- Claude 4.5 Haiku (Non-reasoning)AnthropicQuality Score 27.1Value Score 19.9
- Claude 4.5 Haiku (Reasoning)AnthropicQuality Score 34.4Value Score 24.7
- Claude Sonnet 5 (Adaptive Reasoning, Max Effort)AnthropicQuality Score 64.1Value Score 43.6
- Claude Opus 5 (Adaptive Reasoning, Low Effort)AnthropicQuality Score 68.1Value Score 41.0
- Claude Opus 5 (Adaptive Reasoning, Medium Effort)AnthropicQuality Score 73.1Value Score 44.7