readable AI benchmarks (simplified)
Anthropic
Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback)
Claude Sonnet 5.5 (Adaptive Reasoning, High Effort, Default Fallback) has a Quality Score of 66.2, ranking 30th among 559 scored models. Per 1M tokens, pricing is $2.00 input, $10.00 output, $0.200 cached input, and $2.50 cache write. It has a 1M token context window. Its Reliability Score is 60.5, ranking 53rd among 561 scored models, above average (total average: 35.9). Its Value Score is 43.9, high compared with the total Value average of 31.1.
Quality Score66.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score43.9
Factual reliability60.5
Cache Discount90%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $2.00
- Output
- $10.00
- Cached Input
- $0.200
- Cache write
- $2.50
- Cost per task
- $1.08
Capability
- Intelligence
- 46.7
- Coding
- not available
- Agentic
- not available
- Omniscience
- 20.9
- Correct
- 52.0%
- Blended price
- $1.54
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 83.0%
Correct 52.0%Incorrect 31.0%Partial / not attempted 17.0%
Artificial Analysis benchmarks
- GDPval-AA v2
- 51%
- SciCode
- 54%
- Humanity’s Last Exam
- 46%
- CritPt
- 25%
- AA-Omniscience
- 60%
- AA-LCR
- 78%
Similar models
- Claude Opus 5 (Adaptive Reasoning, Medium Effort)AnthropicQuality Score 67.2Value Score 40.1
- Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)AnthropicQuality Score 69.5Value Score 38.7
- Claude Opus 5.5 (Adaptive Reasoning, Low Effort, Default Fallback)AnthropicQuality Score 67.3Value Score 41.4
- Claude Opus 4.8 (Adaptive Reasoning, Max Effort)AnthropicQuality Score 64.3Value Score 38.4
- Claude Opus 5 (Adaptive Reasoning, High Effort)AnthropicQuality Score 70.4Value Score 42.0
- Claude Opus 4.7 (Adaptive Reasoning, Max Effort)AnthropicQuality Score 63.1Value Score 37.7