readable AI benchmarks (simplified)

readable AI benchmarks

NVIDIA

Nemotron 3 Nano Omni 30B A3B Reasoning

reasoning · open weights · Apr 29, 2026

Nemotron 3 Nano Omni 30B A3B Reasoning has a Quality Score of 18.5, ranking 435th among 572 scored models. Per 1M tokens, pricing is $0.195 input, $1.10 output, and $0.195 cached input. It accepts text, image, video, and audio input, outputs text, and has a 256k token context window. Its Reliability Score is 21.3, ranking 457th among 574 scored models, below average (total average: 36.5). Its Value Score is 15.0, low compared with the total Value average of 31.5.

Quality Score18.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score15.0
Factual reliability21.3
Cache Discount0%

Model specification

Reasoning
reasoning
Input modalities
text, image, video, audio
Output modalities
text
Context window
256k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.195
Output
$1.10
Cached Input
$0.195
Cache write
not available
Cost per task
not available

Capability

Intelligence
10.3
Coding
not available
Agentic
not available
Omniscience
-57.4
Correct
15.2%
Blended price
$0.285

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 87.8%

Correct 15.2%Incorrect 72.6%Partial / not attempted 12.2%

Artificial Analysis benchmarks

GDPval-AA v2
0%
Humanity’s Last Exam
5%
GPQA Diamond
47%
CritPt
0%
AA-Omniscience
21%
AA-LCR
40%

Similar models

Support me! Patreon