Home/Models/INTELLECT-3
prime-intellect logo

INTELLECT-3

by prime-intellect · Released Nov 2025

Open Source
Compare
Context
131K tokens (~66 books)
Input $/1M
$0.20
Output $/1M
$1.10
Type
text
License
Open Source
Benchmarks
4 tested
Data updated today
About

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%).

Capabilities
speed
33.9
#48 globally
Benchmark Scores
Compare All
Tested on 4 benchmarks · Ranked across 2 categories
Score Distribution (all 233 models)
0255075100
Chatbot Arena Elo — Overall

Chatbot Arena overall Elo rating. Crowdsourced human preference ranking from blind head-to-head comparisons across all topics.

1356
Artificial Analysis — Quality Index

Artificial Analysis Quality Index. Composite quality score combining multiple benchmark results into a single metric.

22.2
Artificial Analysis — Agentic Index

Artificial Analysis Agentic Index. Composite score measuring agent capability across tool use and planning tasks.

19.8
Artificial Analysis — Coding Index

Artificial Analysis Coding Index. Composite coding quality score from multiple code benchmarks.

19.1
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Specifications
  • Typetext
  • Context131K tokens (~66 books)
  • ReleasedNov 2025
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.002
Available On
prime-intellect logoprime-intellect$0.20
Categories
Share & Export
Tweet
INTELLECT-3 is an open-source text AI model by prime-intellect, released in November 2025. Context window: 131K tokens.