Trinity Large Thinking
Arcee AI · 1 configuration
Intelligence10.8
Input / 1M$0.25
Output / 1M$0.80
Context512K
Tariff: Arcee AI · Source: artificial-analysis · USD per million tokens
Thinking configuration
What does more thinking buy you?
Compare this model’s measured thinking configurations.
Scroll the chart ↔ · tap a point for details
Efficient frontier: best measured score at each cost1 measured configurations · 0 without both values
Selected: thinking thinking · Click a point to switch configuration
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...
Intelligence IndexArtificial Analysis composite index, not a percentage. Different versions of the index are not directly comparable.
10.8 pointsGPQA DiamondGraduate-level scientific questions. Measures specialist reasoning rather than web-search quality.
75.2 %Humanity’s Last ExamDifficult questions across many disciplines, compared under the same evaluation setup.
15.8 %SciCodeCode generation for scientific research problems.
40.6 %Terminal-Bench 2.1Agent tasks in a terminal environment. Results also depend on the evaluation harness.
20.6 %τ²-BenchTool use and interaction in assistance scenarios. Does not replace an evaluation of your integration.
90.1 %IFBenchVerifiable instruction following. A proxy for precision rather than a benchmark of creative style.
56.3 %Omniscience accuracyFactual accuracy in Artificial Analysis's Omniscience evaluation.
22.5 %Specifications from the catalog
Inputtext
Outputtext
Tool callingYes
Structured outputNo
Speed323.5 tok/s
First token1.33 s
Maximum output80K
Catalog listing date2026-04-01