readable AI benchmarks (simplified)
Anthropic
Claude Fable 5.2 (High, Default Fallback)
Claude Fable 5.2 (High, Default Fallback) has a Quality Score of 71.9, ranking 3rd among 247 scored models. Per 1M tokens, pricing is $8.00 input, $40.00 output, $0.200 cached input, and $10.00 cache write. It has a 1M token context window. Its Reliability Score is 82.0, ranking 3rd among 254 scored models, above average (total average: 46.9). Its Value Score is 41.0, high compared with the total Value average of 28.6.
Quality Score71.9coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score41.0
Factual reliability82.0
Cache Discount98%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $8.00
- Output
- $40.00
- Cached Input
- $0.200
- Cache write
- $10.00
- Cost per task
- $9.08
Capability
- Intelligence
- 61.8
- Omniscience (native net)
- 64.0
- Correct
- 77.2%
- Blended price
- $5.74
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 90.4%
Correct 77.2%Incorrect 13.2%Partial / not attempted 9.6%
Artificial Analysis benchmarks aa-v5
Current Intelligence Index components
- AA-Briefcase v1.1
- 1677.4 Elo
- AutomationBench-AA
- 71.4% private 657-task split from dataset v1.0.6
- GDP.pdf
- 21.8%
- FrontierCode v2.0
- 49.1% AA Stirrup · 132 tasks, 3 attempts per task
- Terminal-Bench v4.0
- 59.6% AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
- AA-Omniscience v1.1
- 64.0 native net
- HLE-Diamond
- 73.8%
- CritPt v2 Hard
- 73.0% AA Stirrup · hard subset, 40 of 70 problems
- Terminal-Bench-Science v0.1.0
- 70.0%
Standalone evaluations
- GDPval-AA v2.1
- 1718.1 Elo
Historical evaluations
- SciCode v1.0.1
- 59.5%
- AA Long Context Reasoning v1.1
- 83.3%
- Humanity's Last Exam
- 66.2%
- CritPt
- 32.9%
- FrontierCode
- 55.9%
Similar models
- Claude Fable 5.2 (Xhigh, Default Fallback)AnthropicQuality Score 72.3Value Score 41.3
- Claude Fable 5.2 (Max, Default Fallback)AnthropicQuality Score 74.0Value Score 42.2
- Claude Fable 5.2 (Medium, Default Fallback)AnthropicQuality Score 69.1Value Score 39.4
- Claude Opus 5.5 (Max, Default Fallback)AnthropicQuality Score 66.6Value Score 41.0
- Claude Fable 5.2 (Low, Default Fallback)AnthropicQuality Score 67.7Value Score 38.6
- Claude Opus 5.5 (Xhigh, Default Fallback)AnthropicQuality Score 64.5Value Score 39.7