readable AI benchmarks (simplified)
Anthropic
Claude Haiku 5.5 (Xhigh, Default Fallback)
Claude Haiku 5.5 (Xhigh, Default Fallback) has a Quality Score of 58.2, ranking 67th among 577 scored models. Per 1M tokens, pricing is $0.100 input, $0.500 output, $0.010 cached input, and $0.125 cache write. It has a 1M token context window. Its Reliability Score is 53.0, ranking 99th among 579 scored models, above average (total average: 36.6). Its Value Score is 53.2, high compared with the total Value average of 31.8.
Quality Score58.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score53.2
Factual reliability53.0
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
- $0.100
- Output
- $0.500
- Cached Input
- $0.010
- Cache write
- $0.125
- Cost per task
- $0.124
Capability
- Intelligence
- 41.2
- Coding
- not available
- Agentic
- not available
- Omniscience
- 6.0
- Correct
- 34.9%
- Blended price
- $0.077
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 63.8%
Correct 34.9%Incorrect 28.9%Partial / not attempted 36.2%
Artificial Analysis benchmarks
- GDPval-AA v2
- 51%
- SciCode
- 52%
- Humanity’s Last Exam
- 43%
- CritPt
- 23%
- AA-Omniscience
- 53%
- AA-LCR
- 78%
Similar models
- Claude Sonnet 5 (Max)AnthropicQuality Score 58.5Value Score 38.8
- Claude Sonnet 5.5 (Medium, Default Fallback)AnthropicQuality Score 61.4Value Score 40.8
- Claude Sonnet 5.5 (Low, Default Fallback)AnthropicQuality Score 57.4Value Score 38.1
- Claude Haiku 5.5 (Max, Default Fallback)AnthropicQuality Score 61.0Value Score 55.8
- Claude Haiku 5.5 (High, Default Fallback)AnthropicQuality Score 55.5Value Score 50.8
- Claude Opus 4.7 (Max)AnthropicQuality Score 63.1Value Score 37.7