readable AI benchmarks (simplified)
Anthropic
Claude Opus 4.5 (Reasoning)
Claude Opus 4.5 (Reasoning) has a Quality Score of 43.0, ranking 78th 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 200k token context window. Its Reliability Score is 57.0, ranking 73rd among 245 scored models, above average (total average: 46.4). Its Value Score is 25.7, around average compared with the total Value average of 28.3.
Quality Score43.0coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score25.7
Factual reliability57.0
Cache Discount90%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 200k 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
- 29.1
- Omniscience (native net)
- 14.0
- Correct
- 46.6%
- Blended price
- $3.85
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 79.2%
Correct 46.6%Incorrect 32.6%Partial / not attempted 20.8%
Artificial Analysis benchmarks legacy records
- Humanity’s Last Exam
- 30%
- GPQA Diamond
- 87%
- CritPt
- 5%
- AA-LCR
- 77%
Similar models
- Claude Sonnet 4.6 (Max)AnthropicQuality Score 43.1Value Score 27.3
- Claude Sonnet 5.5 (Low, Default Fallback)AnthropicQuality Score 42.9Value Score 28.6
- Claude Haiku 5.5 (High)AnthropicQuality Score 41.3Value Score 37.7
- Claude Opus 4.6 (Max)AnthropicQuality Score 44.4Value Score 26.5
- Claude Sonnet 5.5 (Medium, Default Fallback)AnthropicQuality Score 45.1Value Score 30.1
- Claude Sonnet 5 (Xhigh)AnthropicQuality Score 43.0Value Score 28.5