readable AI benchmarks (simplified)

readable AI benchmarks

Amazon

Nova Micro

non-reasoning · closed weights · Dec 3, 2024

Nova Micro has a Quality Score of 17.4, ranking 459th among 571 scored models. Per 1M tokens, pricing is $0.035 input, $0.140 output, and $0.0088 cached input. It accepts text input, outputs text, and has a 130k token context window. Its Reliability Score is 25.7, ranking 385th among 573 scored models, below average (total average: 36.5). Its Value Score is 16.7, low compared with the total Value average of 31.4.

Quality Score17.4coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score16.7
Factual reliability25.7
Cache Discount75%

Model specification

Reasoning
non-reasoning
Input modalities
text
Output modalities
text
Context window
130k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$0.035
Output
$0.140
Cached Input
$0.0088
Cache write
not available
Cost per task
not available

Capability

Intelligence
5.9
Coding
not available
Agentic
not available
Omniscience
-48.5
Correct
10.0%
Blended price
$0.027

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 68.6%

Correct 10.0%Incorrect 58.5%Partial / not attempted 31.4%

Artificial Analysis benchmarks

Humanity’s Last Exam
5%
GPQA Diamond
36%
CritPt
0%
AA-Omniscience
26%
AA-LCR
13%

Similar models

Support me! Patreon