Model Library
Prime IntellectReleased November 27, 2025INTELLECT-3
Prime Intellect · Released November 27, 2025
Intelligence score
16
At a glance
- Intelligence
- 16
- Speed
- —
- Latency
- —
- Input price
- Not published
- Output price
- Not published
- Context window
- 130Ktokens
- Parameters
- 107billions
Summary
Comparison summary
INTELLECT-3 scores 16 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9).
Specifications
Technical specifications
| Model name | INTELLECT-3 |
|---|---|
| Provider | Prime Intellect |
| Release date | November 27, 2025 |
| Intelligence score | 16 |
| Speed | — |
| Latency (TTFT) | — |
| Input price | Not published |
| Output price | Not published |
| Context window | 130,000 tokens |
| Parameters | 107B |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | MIT |
| API availability | — |
| Source | Model Intelligence legacy profile: intellect-3 |
FAQ · 16
Frequently asked questions
INTELLECT-3 was released on November 27, 2025.
INTELLECT-3 was created by Prime Intellect.
INTELLECT-3 scores 16 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 9).
Yes, INTELLECT-3 is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
INTELLECT-3 supports text input.
INTELLECT-3 supports text output.
No, INTELLECT-3 does not support image input. It can only process text.
No, INTELLECT-3 is not multimodal. It only supports text input.
INTELLECT-3 has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, INTELLECT-3 is open weights. The model weights are publicly available and can be downloaded for self-hosting.
INTELLECT-3 has 107 billion parameters (12 billion active).
INTELLECT-3 is a Mixture of Experts (MoE) model with 107 billion total parameters, but only 12 billion active parameters are used during inference.
INTELLECT-3 is released under the MIT license. This license allows commercial use.
INTELLECT-3 achieves a score of 16 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
INTELLECT-3 is an open weights model that can be self-hosted.
INTELLECT-3 is an open weights model that can be downloaded and self-hosted.