Prime Intellect: INTELLECT-3
Analysis Summary
INTELLECT-3 from Prime Intellect has an intelligence index of 15.6 and a coding index of 19.1, placing it in the limited tier for general reasoning and coding tasks. Its math index of 88 and AIME score of 0.88 are disproportionately strong, suggesting a model tuned for mathematical reasoning. MMLU Pro at 0.822 and GPQA at 0.761 show reasonable knowledge breadth. Tool use and function calling are supported.
For businesses, the math strength and tool use capability make it a candidate for quantitative analysis or structured data tasks, but the low agentic index of 17.8 and weak coding scores limit its role in software engineering or complex automation. Instruction following is below average. The 131K context window is adequate.
At $0.20 input and $1.10 output, pricing is moderate but output costs are relatively high for the capability level. Prime Intellect is a newer provider without the enterprise track record of established names. This model suits narrow mathematical or analytical use cases rather than broad business deployment.
Assessed June 17, 2026
Editorial notes
Prime Intellect's INTELLECT-3 shows strong math and AIME performance with tool use support, but reasoning and coding indices are limited, and the provider is less established for enterprise business workflows.
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 #165 of 380 AI models we track for overall intelligence, #153 of 317 for coding, #196 of 292 for agentic tasks. Its 131K-token context window is larger than 59% 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 #153 of 317 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.
