Back to Rankings

Arcee AI
Trinity Mini

Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function calling and multi-step agent workflows.

Share

Model details

Context window131,072 tokens
Max completion size69 tokens
Prompt cost / 1K tokens$0.000000045
Completion cost / 1K tokens$0.00000015
Accepts
Produces

Benchmark performance

Overall

56
score
28th
placement

Cost

98
score
3rd
placement

Logic

80
score
7th
placement

Speed

62
score
28th
placement

Scoring

16
score
22nd
placement

Tool Use

6
score
11th
placement

Hallucination

74
score
10th
placement

Classification

10
score
5th
placement

Structured Output

75
score
4th
placement

Pricing

Usage pricing
Prompt
$0.000000045
Completion
$0.00000015
Request
FREE
Image
FREE
Web Search
FREE
Internal Reasoning
FREE

Best Overall scoring LLMs

xAI

Grok 4 Fast

88
score
1st
placement
Qwen

Qwen3 VL 235B A22B Instruct

86
score
2nd
placement
xAI

Grok 4.1 Fast

84
score
3rd
placement
OpenAI

GPT-5.1 Chat

82
score
4th
placement
OpenAI

GPT-5.1-Codex

82
score
4th
placement
Anthropic

Claude Haiku 4.5

80
score
5th
placement
Browse all LLMs