readable AI benchmarks (simplified)
Anthropic
Claude Opus 5.5 (High, Default Fallback)
Claude Opus 5.5 (High, Default Fallback) has a Quality Score of 61.5, ranking 12th among 238 scored models. Per 1M tokens, pricing is $4.00 input, $20.00 output, $0.200 cached input, and $5.00 cache write. It has a 1M token context window. Its Reliability Score is 71.2, ranking 11th among 245 scored models, above average (total average: 46.4). Its Value Score is 37.8, high compared with the total Value average of 28.3.
Quality Score61.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score37.8
Factual reliability71.2
Cache Discount95%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $4.00
- Output
- $20.00
- Cached Input
- $0.200
- Cache write
- $5.00
- Cost per task
- $3.46
Capability
- Intelligence
- 51.8
- Omniscience (native net)
- 42.4
- Correct
- 64.8%
- Blended price
- $2.94
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 87.3%
Correct 64.8%Incorrect 22.5%Partial / not attempted 12.7%
Artificial Analysis benchmarks aa-v5
Current Intelligence Index components
- AA-Briefcase v1.1
- 1682.4 Elo
- AutomationBench-AA
- 63.2% private 657-task split from dataset v1.0.6
- GDP.pdf
- 28.8%
- FrontierCode v2.0
- 35.9% AA Stirrup · 132 tasks, 3 attempts per task
- Terminal-Bench v4.0
- 56.6% AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
- AA-Omniscience v1.1
- 42.4 native net
- HLE-Diamond
- 55.6%
- CritPt v2 Hard
- 59.5% AA Stirrup · hard subset, 40 of 70 problems
- Terminal-Bench-Science v0.1.0
- 49.0%
Standalone evaluations
- GDPval-AA v2.1
- 1713.6 Elo
Historical evaluations
- SciCode v1.0.1
- 60.4%
- AA Long Context Reasoning v1.1
- 82.7%
- Humanity's Last Exam
- 55.6%
- CritPt
- 30.9%
- FrontierCode
- 54.0%
Similar models
- Claude Fable 5.1 (Xhigh, Default Fallback)AnthropicQuality Score 61.1Value Score 34.0
- Claude Fable 5.1 (Max, Default Fallback)AnthropicQuality Score 61.1Value Score 34.1
- Claude Sonnet 5.5 (Max, Default Fallback)AnthropicQuality Score 59.9Value Score 40.0
- Claude Opus 5 (Xhigh)AnthropicQuality Score 58.7Value Score 35.0
- Claude Opus 5.5 (Medium, Default Fallback)AnthropicQuality Score 59.0Value Score 36.3
- Claude Fable 5.1 (High, Default Fallback)AnthropicQuality Score 58.6Value Score 32.6