Arcee Trinity Large (Thinking) — benchmark results

Arcee Trinity Large evaluated with thinking enabled. Provider: Arcee AI. Released 2026-04-01. Access: Open.

Unified ELO 1611 ± 20, rank #454 of 1776 rated models, from 26 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Position Bias (Lechmazur)36.6Order Flip % (lower is better)62.9
Chatbot Arena (Text)1369Elo56.6
PACT (Lechmazur)1526CMS Points56
SpeechMap Compliance65.5% Requests Completed54.5
BenchLM52.3Overall Score50.8
Vals AI CaseLaw v257.88Accuracy (%)47.7
PM-LLM-Benchmark30.2Score45.3
Bullshit Benchmark20BS Detection Rate (%)42.2
Design Arena (Website)1162Elo40.4
Design Arena (3D)1139Elo39.8
SnakeBench19.6TrueSkill Rating37.7
Design Arena (Game Dev)1134Elo31.4

Interactive version: theaggregate.ai/model?slug=arcee-trinity-large-thinking · How the rankings work · Data refreshed daily, snapshot 2026-07-22.