Skip to content
llmwaves

Trinity Large Thinking

Arcee AI · released Apr 1, 2026

Open weightsReasoningTool use

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...

Specification

Context window
262K
Max output
80K
Knowledge cutoff
Not stated
Parameters
398.6B
Licence
other
Serving providers
1
Moderated
No
Uptime
100.0%

Intelligence

10.8

44th percentile

Coding

25.8

Coding Index

Agentic

1.0

Agentic Index

Output speed

246 t/s

Median across providers

Latency

714ms

Time to first token

Cost per task

$0.08

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • τ²-bench (Telecom)
    90.1%
  • GPQA Diamond
    75.2%
  • IFBench
    56.3%
  • SciCode
    40.6%
  • AA-LCR (long context)
    38.0%
  • Terminal-Bench Hard
    22.7%
  • Humanity's Last Exam
    15.8%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
τ²-bench (Telecom)90.1%
GPQA Diamond75.2%
IFBench56.3%
SciCode40.6%
AA-LCR (long context)38.0%
Terminal-Bench Hard22.7%
Humanity's Last Exam15.8%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
Qwen3.5-9B11.2
Granite 4.2 8B11.1
GLM 4.5 Air11.1
Qwen3 VL 32B Instruct11.0
o3 Mini High11.0
Trinity Large Thinking10.8
Mercury 210.8
Nemotron 3 Nano Omni (free)10.3

Percentile among all indexed models

Intelligence44th
Coding31th
Agentic2th
Terminal work62th
Arena Elo34th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$0.25
Output / 1M tokens
$0.8
Cached input / 1M
$0.06
Blended 3:1
$0.388

One task, estimated

$0.08

Input tokens
50,000
Output tokens
80,000
Profile
Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.

Arena

Head-to-head generation quality

Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.

Overall Elo
1,139
Win rate
41.3%
Strongest at
Websites
Tournaments
7,091

Elo by category

Dot position on a 1,000–1,150 scale · Elo has no meaningful zero

Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.

View as table
CategoryEloWin rate
Websites113941.3%
Data visualisation109839.3%
Game development108238.4%
3D scenes108241.3%
UI components104632.6%
SVG101535.2%