readable AI benchmarks (simplified)
Anthropic
Claude Opus 4.6 (Max)
Claude Opus 4.6 (Max) has a Quality Score of 44.4, ranking 68th among 238 scored models. Per 1M tokens, pricing is $5.00 input, $25.00 output, $0.500 cached input, and $6.25 cache write. It has a 1M token context window. Its Reliability Score is 56.8, ranking 75th among 245 scored models, above average (total average: 46.4). Its Value Score is 26.5, around average compared with the total Value average of 28.3.
Quality Score44.4coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score26.5
Factual reliability56.8
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
- $5.00
- Output
- $25.00
- Cached Input
- $0.500
- Cache write
- $6.25
- Cost per task
- not available
Capability
- Intelligence
- 31.9
- Omniscience (native net)
- 13.7
- Correct
- 47.0%
- Blended price
- $3.85
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 80.3%
Correct 47.0%Incorrect 33.3%Partial / not attempted 19.7%
Artificial Analysis benchmarks legacy records
- Humanity’s Last Exam
- 40%
- GPQA Diamond
- 90%
- CritPt
- 13%
- AA-LCR
- 78%
Similar models
- Claude Sonnet 5.5 (Medium, Default Fallback)AnthropicQuality Score 45.1Value Score 30.1
- Claude Haiku 5.5 (Xhigh)AnthropicQuality Score 44.3Value Score 40.5
- Claude Sonnet 4.6 (Max)AnthropicQuality Score 43.1Value Score 27.3
- Claude Sonnet 5 (Xhigh)AnthropicQuality Score 43.0Value Score 28.5
- Claude Opus 4.5 (Reasoning)AnthropicQuality Score 43.0Value Score 25.7
- Claude Haiku 5.5 (High)AnthropicQuality Score 41.3Value Score 37.7