readable AI benchmarks

NVIDIA

Nemotron 3.5 Lightning

reasoning · open weights · Aug 11, 2026

Quality Score24.3
Value Score24.8
Reliability41.1
Cache Discount29%

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
1M tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.070
Output
$0.220
Cached Input
$0.050
Cached Output
not available
Cost per task
$0.076

Capability

Intelligence
23.6
Coding
26.8
Agentic
13.8
Omniscience
-17.7
Correct
14.4%
Blended price
$0.071

Answer outcomes

Correct 14.4%Incorrect 32.2%Abstained 53.4%

Artificial Analysis benchmarks

GDPval-AA v2
16%
τ³-Banking
9%
Terminal-Bench v2.1
24%
SciCode
32%
Humanity’s Last Exam
11%
GPQA Diamond
74%
CritPt
0%
AA-Omniscience
41%
AA-LCR
55%

Similar models