readable AI benchmarks (simplified)

readable AI benchmarks

Anthropic

Claude Opus 4.5 (Reasoning)

reasoning · closed weights · Nov 24, 2025

Claude Opus 4.5 (Reasoning) has a Quality Score of 50.9, ranking 86th among 551 scored models. Per 1M tokens, pricing is $5.00 input, $25.00 output, $0.500 cached input, and $6.25 cache write. It has a 200k token context window. Its Reliability Score is 57.0, ranking 68th among 553 scored models, above average (total average: 35.6). Its Value Score is 30.4, around average compared with the total Value average of 30.7.

Quality Score50.9coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score30.4
Factual reliability57.0
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
200k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$5.00
Output
$25.00
Cached Input
$0.500
Cache write
$6.25
Cost per task
not available

Capability

Intelligence
29.1
Coding
not available
Agentic
not available
Omniscience
14.0
Correct
46.6%
Blended price
$3.85

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 79.2%

Correct 46.6%Incorrect 32.6%Partial / not attempted 20.8%

Artificial Analysis benchmarks

Humanity’s Last Exam
30%
GPQA Diamond
87%
CritPt
5%
AA-Omniscience
57%
AA-LCR
77%

Similar models

Support me! Patreon