Prime Intellect: INTELLECT-3
Analysis Summary
INTELLECT-3 from Prime Intellect is a mid-tier reasoning model with a strong math index and above-average GPQA and MMLU Pro scores for its intelligence tier. Tool use and function calling are supported, and the 131K context window is adequate for most business tasks. However, coding and agentic scores are modest, and long-context reasoning is weak.
For businesses, this model is best suited to analytical and research tasks where math and science reasoning matter. It is not well-positioned for autonomous agent workflows, complex coding, or long-document analysis. Instruction following is limited, which reduces reliability for client-facing content generation.
At $0.20 input but $1.10 output per million tokens, the cost structure is unfavourable compared to stronger models in a similar intelligence range. Teams should evaluate whether the math and science strengths justify the pricing before adopting it for production use.
Assessed June 6, 2026
Editorial notes
Prime Intellect INTELLECT-3 shows strong math and science reasoning with decent MMLU Pro scores, but coding and agentic performance are limited and output pricing is high relative to its capability tier.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Prime Intellect: INTELLECT-3 compares
Prime Intellect: INTELLECT-3 ranks #161 of 375 AI models we track for overall intelligence, #152 of 312 for coding, #192 of 286 for agentic tasks. Its 131K-token context window is larger than 60% of the models we list. At $0.20 per million input tokens it is cheaper than 53% of comparable models.
About 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,..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Prime Intellect: INTELLECT-3 stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
prime-intellect/intellect-3
|
| Provider | prime-intellect |
| Release Date | November 27, 2025 |
| Context Length | 131,072 tokens |
| Max Completion | 131,072 tokens |
| Status | Active |
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.
Leaderboard Categories
External Resources
Frequently asked questions about Prime Intellect: INTELLECT-3
How much does Prime Intellect: INTELLECT-3 cost?
Prime Intellect: INTELLECT-3 costs $0.20 per million input tokens and $1.10 per million output tokens.
What is the context window of Prime Intellect: INTELLECT-3?
Prime Intellect: INTELLECT-3 has a context window of 131,072 tokens (131K).
Is Prime Intellect: INTELLECT-3 good for coding?
On our coding benchmark index, Prime Intellect: INTELLECT-3 ranks #152 of 312 models, placing it in the broader range of the field for code generation and debugging.
What can Prime Intellect: INTELLECT-3 do?
Prime Intellect: INTELLECT-3 supports tool use and function calling.
Who created Prime Intellect: INTELLECT-3?
Prime Intellect: INTELLECT-3 is developed by Prime Intellect and was released on November 27, 2025.
