readable AI benchmarks (simplified)

readable AI benchmarks

Anthropic

Claude Opus 5.5 (Adaptive Reasoning, Low Effort, Default Fallback)

reasoning · closed weights · Sep 17, 2026

Claude Opus 5.5 (Adaptive Reasoning, Low Effort, Default Fallback) has a Quality Score of 66.4, ranking 18th 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 69.4, ranking 13th among 282 scored models, above average (total average: 36.9). Its Value Score is 38.3, high compared with the total Value average of 30.3.

Quality Score66.4coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1
Value Score38.3
Reliability69.4
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
$0.551

Capability

Intelligence
42.3
Coding
not available
Agentic
not available
Omniscience
38.9
Correct
63.5%
Blended price
$2.94

Answer outcomes

Attempt rate: 88.2%

Correct 63.5%Incorrect 24.7%Abstained 11.8%

Artificial Analysis benchmarks

GDPval-AA v2
36%
SciCode
59%
Humanity’s Last Exam
48%
CritPt
18%
AA-Omniscience
69%
AA-LCR
81%

Similar models

Support me! Ko-Fi