readable AI benchmarks (simplified)

readable AI benchmarks

Claude Opus 5.5 (Adaptive Reasoning, Max Effort, Default Fallback) has a Quality Score of 75.7, ranking 1st 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 accepts text, image, and pdf input, outputs text, and has a 1M token context window. Its Reliability Score is 73.2, ranking 1st among 282 scored models, above average (total average: 36.9). Its Value Score is 47.9, high compared with the total Value average of 30.3.

Quality Score75.7coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1

Value Score47.9

Reliability73.2

Cache Discount95%

Model specification

Reasoning: reasoning
Input modalities: text, image, pdf
Output modalities: text
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: $5.98

Capability

Intelligence: 57.6
Coding: not available
Agentic: not available
Omniscience: 46.4
Correct: 66.2%
Blended price: $2.94

Answer outcomes

Attempt rate: 86.0%

Correct 66.2%Incorrect 19.8%Abstained 14.0%

Artificial Analysis benchmarks

GDPval-AA v2: 67%
SciCode: 67%
Humanity’s Last Exam: 61%
CritPt: 32%
AA-Omniscience: 73%
AA-LCR: 85%

Similar models

Graph Open on Artificial Analysis