Benchmarks

Prime Intellect: INTELLECT-3

prime-intellect/intellect-3

INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It offers state-of-the-art performance for its size across math,...

Prompt $/1M
$0.200
Completion $/1M
$1.100
Context
131,072 tok
Best provider
58 tok/s · Nebius

Specs

Model id
prime-intellect/intellect-3
Display name
Prime Intellect: INTELLECT-3
Modality
text->text
Tokenizer
Other
Instruct type
Context length
131,072
Max completion
131,072
Prompt $/1M
$0.200
Completion $/1M
$1.100
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
Nebiusfastest58
prime-intellectfastest
Artificial Analysis0
Prime Intellect: INTELLECT-3 - Benchmarks, Pricing and Speed | TryAii