readable AI benchmarks (simplified)
Anthropic
Claude Haiku 5.5 (Medium, Default Fallback)
Claude Haiku 5.5 (Medium, Default Fallback) has a Quality Score of 52.6, ranking 97th 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 52.2, ranking 107th among 579 scored models, above average (total average: 36.6). Its Value Score is 48.1, high compared with the total Value average of 31.8.
Quality Score52.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score48.1
Factual reliability52.2
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
- $0.047
Capability
- Intelligence
- 34.5
- Coding
- not available
- Agentic
- not available
- Omniscience
- 4.5
- Correct
- 34.0%
- Blended price
- $0.077
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 63.6%
Correct 34.0%Incorrect 29.6%Partial / not attempted 36.4%
Artificial Analysis benchmarks
- GDPval-AA v2
- 39%
- SciCode
- 49%
- Humanity’s Last Exam
- 34%
- CritPt
- 13%
- AA-Omniscience
- 52%
- AA-LCR
- 77%
Similar models
- Claude Sonnet 5 (Xhigh)AnthropicQuality Score 52.2Value Score 34.7
- Claude Opus 4.6 (Max)AnthropicQuality Score 53.0Value Score 31.6
- Claude Sonnet 4.6 (Max)AnthropicQuality Score 51.2Value Score 32.4
- Claude Haiku 5.5 (High, Default Fallback)AnthropicQuality Score 55.5Value Score 50.8
- Claude Opus 4.5 (Reasoning)AnthropicQuality Score 50.9Value Score 30.4
- Claude Sonnet 5.5 (Low, Default Fallback)AnthropicQuality Score 57.4Value Score 38.1