Context
262K tokens (~131 books)
Input $/1M
$0.22
Output $/1M
$0.85
Type
text
License
Open Source
Benchmarks
3 tested
Data updated today
About
Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7
Tested on 3 benchmarks with 0.0% average. Top scores: Artificial Analysis — Agentic Index (42.6%), Artificial Analysis — Quality Index (31.9%), Artificial Analysis — Coding Index (27.2%).
Capabilities
speed
56.5
#31 globally
Benchmark Scores
Compare AllTested on 3 benchmarks · Ranked across 1 categories
Score Distribution (all 231 models)
0255075100
speedCompare speed →
Artificial Analysis — Agentic Index
42.6—Artificial Analysis Agentic Index. Composite score measuring agent capability across tool use and planning tasks.
Artificial Analysis — Quality Index
31.9—Artificial Analysis Quality Index. Composite quality score combining multiple benchmark results into a single metric.
Artificial Analysis — Coding Index
27.2—Artificial Analysis Coding Index. Composite coding quality score from multiple code benchmarks.
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Info
Research
Documentation
Community
Source Code
BenchGecko API
trinity-large-thinking
Specifications
- Typetext
- Context262K tokens (~131 books)
- ReleasedApr 2026
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.001
Available On
Categories
Share & Export
Frequently Asked Questions
Trinity Large Thinking is an open-source text AI model by arcee-ai, released in April 2026. Context window: 262K tokens.