readable AI benchmarks (simplified)

readable AI benchmarks

Claude Opus 5.5 (Low, Default Fallback) has a Quality Score of 52.1, ranking 40th among 237 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 69.5, ranking 21st among 245 scored models, above average (total average: 46.4). Its Value Score is 32.1, around average compared with the total Value average of 28.3.

Quality Score52.1coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available

Value Score32.1

Factual reliability69.5

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: $0.976

Capability

Intelligence: 34.8
Omniscience (native net): 39.0
Correct: 63.3%
Blended price: $2.94

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 87.6%

Correct 63.3%Incorrect 24.3%Partial / not attempted 12.4%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1: 1279.0 Elo
AutomationBench-AA: 52.9%
GDP.pdf: 25.6%
FrontierCode v2.0: 15.8%
Terminal-Bench v4.0: 31.3%
AA-Omniscience v1.1: 39.0 native net
HLE-Diamond: 41.7%
CritPt v2 Hard: 36.0%
Terminal-Bench-Science v0.1.0: 24.3%

Standalone evaluations

GDPval-AA v2.1: 1240.2 Elo

Historical evaluations

SciCode v1.0.1: 58.6%
AA Long Context Reasoning v1.1: 80.7%
Humanity's Last Exam: 48.3%
CritPt: 17.7%
FrontierCode: 42.7%

Similar models

Graph Open on Artificial Analysis