readable AI benchmarks (simplified)

readable AI benchmarks

Claude Opus 5.5 (Adaptive Reasoning, Medium Effort, Default Fallback) has a Quality Score of 71.0, ranking 10th among 282 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 70.2, ranking 12th among 282 scored models, above average (total average: 36.9). Its Value Score is 43.6, high compared with the total Value average of 30.3.

Quality Score71.0coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1

Value Score43.6

Reliability70.2

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: $1.34

Capability

Intelligence: 51.2
Coding: not available
Agentic: not available
Omniscience: 40.3
Correct: 64.5%
Blended price: $2.94

Answer outcomes

Attempt rate: 88.8%

Correct 64.5%Incorrect 24.2%Abstained 11.2%

Artificial Analysis benchmarks

GDPval-AA v2: 54%
SciCode: 59%
Humanity’s Last Exam: 55%
CritPt: 28%
AA-Omniscience: 70%
AA-LCR: 84%

Similar models

Graph Open on Artificial Analysis