readable AI benchmarks (simplified)

readable AI benchmarks

Amazon

Nova Lite

non-reasoning · closed weights · Dec 3, 2024

Nova Lite has a Quality Score of 19.6, ranking 393rd among 551 scored models. Per 1M tokens, pricing is $0.060 input, $0.240 output, and $0.015 cached input. It accepts text, image, video, and pdf input, outputs text, and has a 300k token context window. Its Reliability Score is 28.9, ranking 317th among 553 scored models, below average (total average: 35.6). Its Value Score is 18.4, low compared with the total Value average of 30.7.

Quality Score19.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score18.4
Factual reliability28.9
Cache Discount75%

Model specification

Reasoning
non-reasoning
Input modalities
text, image, video, pdf
Output modalities
text
Context window
300k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$0.060
Output
$0.240
Cached Input
$0.015
Cache write
not available
Cost per task
not available

Capability

Intelligence
6.7
Coding
not available
Agentic
not available
Omniscience
-42.2
Correct
9.8%
Blended price
$0.047

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 61.8%

Correct 9.8%Incorrect 52.0%Partial / not attempted 38.2%

Artificial Analysis benchmarks

Humanity’s Last Exam
4%
GPQA Diamond
43%
CritPt
0%
AA-Omniscience
29%
AA-LCR
19%

Similar models

Support me! Patreon