#33

Trinity Large Preview (free)

Arcee Ai · Release: 2026-01-27 · arcee-ai/trinity-large-preview:free::none

Avg Score

4.34

Cost per result

0.000

Consistency

9.97

Total Cost

$0.000

Tests Correct

5

A test is fully passed only if every run passed for that test.

Wrong Tests

9

Attempt pass rate: 35.7%

Flaky tests

0

Response time: avg 2.78s · total 38.86s · max 8.17s

Wrong answer: 8 Did not follow instructions: 1

Top Models by Score

Choose the first model, then click a second model to open a side-by-side page.

#27 MiniMax M2.5 5.65

#28 Qwen3.5-122B-A10B 5.20

#29 GPT-4o-mini 4.86

#30 DeepSeek V3.2 4.70

#31 Qwen3.5-27B 4.70

#32 Qwen3.5-35B-A3B 4.63

#33 Trinity Large Preview (free) 4.34

#34 GLM 4.7 Flash 4.15

#35 Kimi K2.5 4.08

#36 Qwen3 Coder Next 3.72

#37 GLM 4.7 Flash 3.63

#38 Qwen3.5-Flash 3.63

#39 Qwen3 Coder Next 3.50

Category	Avg Score	Consistency	Tests Correct
Anti-AI Tricks	1.00	10.00	0/3
Data parsing and extraction	9.88	10.00	2/2
Domain specific	4.00	10.00	1/3
Instructions following	2.00	9.79	0/2
Puzzle Solving	4.00	10.00	1/3
Tool Calling	10.00	10.00	1/1