Arcee Trinity Large (Thinking): benchmark results

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

Unified ELO 1572 ± 1, rank #547 of 1761 rated models, from 48 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Position Bias (Lechmazur)36.6Order Flip % (lower is better)62.9
Chatbot Arena (Text - Math)1385Arena Score56.7
PACT (Lechmazur)1526PACT Bilateral Rating56
SpeechMap Compliance65.5% Requests Completed55.7
Chatbot Arena (Text - Hard Prompts)1386Arena Score54.9
Chatbot Arena (Text)1369Elo54.5
Chatbot Arena (Text - Instruction Following)1358Arena Score54.4
Chatbot Arena (Text - English)1384Arena Score54.1
Chatbot Arena (Text - Creative Writing)1334Arena Score53.9
Chatbot Arena (Text - Coding)1414Arena Score53.6
Chatbot Arena (Text - Chinese)1397Arena Score52.8
Chatbot Arena (Text - Japanese)1339Arena Score52.3

Interactive version: theaggregate.ai/model?slug=arcee-trinity-large-thinking · How It Works · Data refreshed daily, snapshot 2026-09-05.