readable AI benchmarks (simplified)
Anthropic
Claude Sonnet 4.6 (Non-reasoning, Low)
Claude Sonnet 4.6 (Non-reasoning, Low) has a Quality Score of 42.4, ranking 169th among 572 scored models. Per 1M tokens, pricing is $3.00 input, $15.00 output, $0.300 cached input, and $3.75 cache write. It has a 1M token context window. Its Reliability Score is 49.0, ranking 140th among 574 scored models, above average (total average: 36.5). Its Value Score is 26.8, low compared with the total Value average of 31.5.
Quality Score42.4coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score26.8
Factual reliability49.0
Cache Discount90%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $3.00
- Output
- $15.00
- Cached Input
- $0.300
- Cache write
- $3.75
- Cost per task
- not available
Capability
- Intelligence
- 23.3
- Coding
- not available
- Agentic
- not available
- Omniscience
- -2.1
- Correct
- 36.5%
- Blended price
- $2.31
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 75.1%
Correct 36.5%Incorrect 38.6%Partial / not attempted 24.9%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 11%
- GPQA Diamond
- 80%
- CritPt
- 1%
- AA-Omniscience
- 49%
- AA-LCR
- 69%
Similar models
- Claude Sonnet 5 (Non-reasoning, High)AnthropicQuality Score 42.7Value Score 28.3
- Claude Opus 4.5 (Non-reasoning)AnthropicQuality Score 42.2Value Score 25.2
- Claude Sonnet 4.6 (Non-reasoning, High)AnthropicQuality Score 43.1Value Score 27.3
- Claude Opus 4.6 (Non-reasoning, High)AnthropicQuality Score 45.9Value Score 27.4
- Claude 4.5 Sonnet (Non-reasoning)AnthropicQuality Score 37.5Value Score 23.8
- Claude 4 Sonnet (Non-reasoning)AnthropicQuality Score 35.5Value Score not available