readable AI benchmarks (simplified)
Anthropic
Claude 4 Sonnet (Reasoning)
Claude 4 Sonnet (Reasoning) has a Quality Score of 34.5, ranking 125th among 238 scored models. It has a 1M token context window. Its Reliability Score is 50.1, ranking 107th among 245 scored models, above average (total average: 46.4).
Quality Score34.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability50.1
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- not available
- Output
- not available
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 18.9
- Omniscience (native net)
- 0.2
- Correct
- 22.7%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 45.2%
Correct 22.7%Incorrect 22.5%Partial / not attempted 54.8%
Artificial Analysis benchmarks legacy records
- Legacy GDPval-AA (normalized)
- 10%
- τ³-Banking
- 17%
- Humanity’s Last Exam
- 11%
- GPQA Diamond
- 78%
- CritPt
- 0%
- AA-LCR
- 70%
Similar models
- Claude Haiku 5.5 (Low)AnthropicQuality Score 34.9Value Score 31.9
- Claude 3.7 Sonnet (Reasoning)AnthropicQuality Score 33.7Value Score not available
- Claude 4.5 Sonnet (Reasoning)AnthropicQuality Score 35.3Value Score 22.3
- Claude 4.5 Haiku (Reasoning)AnthropicQuality Score 32.3Value Score 23.4
- Claude Sonnet 5 (Low)AnthropicQuality Score 35.1Value Score 23.3
- Claude Haiku 5.5 (Medium)AnthropicQuality Score 38.3Value Score 35.1