Prime Intellect: INTELLECT-3
Prime Intellect's INTELLECT-3 shows limited benchmark performance across reasoning, coding, and agentic tasks, placing it well below the competitive tier for professional business use. At its price point there are significantly stronger alternatives available, and it is best suited to experimental or niche applications.
Assessment date: March 14, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
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, code, science, and general reasoning, consistently outperforming many larger frontier models. Designed for strong multi-step problem solving, it maintains high accuracy on structured tasks while remaining efficient at inference thanks to its MoE architecture.
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | Other |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Evaluations
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.20 | $0.000200 |
| Output | $1.10 | $0.001100 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
