Benchmarks

NVIDIA: Nemotron 3 Super

nvidia/nemotron-3-super-120b-a12b

Nemotron 3 Super is a NVIDIA model that isn't ranked on the TryAii Score yet — only 2 benchmarks on file so far. It lists at $0.085/$0.4 per million input/output tokens with a 1M-token context. It's reasonably quick at roughly 36-53 tokens/sec.

Prompt $/1M
$0.085
Completion $/1M
$0.400
Context
1,000,000 tok
Best provider
74 tok/s · Nebius

Specs

Model id
nvidia/nemotron-3-super-120b-a12b
Display name
NVIDIA: Nemotron 3 Super
Modality
text->text
Tokenizer
Other
Instruct type
Context length
1,000,000
Max completion
16,384
Prompt $/1M
$0.085
Completion $/1M
$0.400
Free tier
no

Capabilities

  • Function callingno
  • JSON modeno
  • System promptno
  • Visionno
  • Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Providertok/s
Nebiusfastest74
DeepInfrafastest46
DekaLLM45
DigitalOcean11