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,...
Tested on 4 benchmarks. Top scores: Chatbot Arena Elo — Overall (1356.5%), Artificial Analysis — Agentic Index (19.8%), Artificial Analysis — Coding Index (19.1%).
Chatbot Arena overall Elo rating. Crowdsourced human preference ranking from blind head-to-head comparisons across all topics.
Artificial Analysis Agentic Index. Composite score measuring agent capability across tool use and planning tasks.
Artificial Analysis Coding Index. Composite coding quality score from multiple code benchmarks.
Artificial Analysis Quality Index. Composite quality score combining multiple benchmark results into a single metric.
- Typetext
- Context131K tokens (~66 books)
- ReleasedNov 2025
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.002
Frequently Asked Questions
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteGemma 3 12B (free) · Google DeepMindQwen3 Next 80B A3B Instruct (free) · Alibaba QwenKey facts · as of 2026-06-23
- INTELLECT-3 by prime-intellect. Not enough public benchmark scores to rank yet.
- List price $0.20 input · $1.10 output per 1M tokens (as of 2026-06-23).
How to cite · data as of 2026-06-23
INTELLECT-3 · benchmarks, pricing and providers. BenchGecko, data as of 2026-06-23. https://benchgecko.ai/model/intellect-3
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP