MMODELYST
Models/NVIDIA Nemotron Nano 12B v2 VL
MDL

NVIDIA Nemotron Nano 12B v2 VL

NVIDIA

Verified against Artificial Analysis · Jul 13, 2026
Capability
55
percentile index
Price /M
$0.2 / $0.6
in / out
Context
Avg score
40.7
10 benchmarks
AA Intelligence
9.0
index
Speed
300 tok/s
TTFT 0.2s
Released
Oct 28, 2025
About

NVIDIA Nemotron Nano 12B v2 VL is a open-weights model in the NVIDIA family from NVIDIA. Benchmarked on 10 evals, averaging 40.7.

Benchmark scores · 10
avg 40.7 — higher is better
MMLU-Pro
75.9
AIME
75
LiveCodeBench
69.4
GPQA Diamond
57.2
AA Long-Context Reasoning
40
IFBench
31.9
SciCode
26.2
τ²-bench
21.3
Humanity's Last Exam
5.3
Terminal-Bench Hard
4.5
Details
PublisherNVIDIA
FamilyNVIDIA
Parameters
License
WeightsOpen
ReleasedOct 28, 2025
Performance & price
Output speed300 tok/s
Latency (TTFT)0.2s
First answer6.9s
Price in / out$0.2 / $0.6 per 1M
Blended price$0.3 / 1M
Math index75.0

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$0.6/M