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 with 0.0% average. Top scores: Chatbot Arena Elo — Overall (1356.2%), Artificial Analysis — Quality Index (22.2%), Artificial Analysis — Agentic Index (19.8%).
Chatbot Arena overall Elo rating. Crowdsourced human preference ranking from blind head-to-head comparisons across all topics.
Artificial Analysis Quality Index. Composite quality score combining multiple benchmark results into a single metric.
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.
- Typetext
- Context131K tokens (~66 books)
- ReleasedNov 2025
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.002