readable AI benchmarks

Amazon

Nova 2.0 Pro Preview (medium)

reasoning · closed weights · Nov 27, 2025

Quality Score22.1
Value Score18.0
Reliability25.5
Cache Discount75%

Model specification

Reasoning
reasoning
Input modalities
text, image
Output modalities
text
Context window
256k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$1.25
Output
$10.00
Cached Input
$0.312
Cached Output
not available
Cost per task
not available

Capability

Intelligence
22.1
Coding
34.0
Agentic
not available
Omniscience
-49.0
Correct
22.0%
Blended price
$1.47

Answer outcomes

Correct 22.0%Incorrect 71.0%Abstained 7.0%

Artificial Analysis benchmarks

GDPval-AA v2
9%
Terminal-Bench v2.1
30%
SciCode
43%
Humanity’s Last Exam
9%
GPQA Diamond
78%
CritPt
0%
AA-Omniscience
25%
AA-LCR
58%

Similar models