AI BENCHY
Advertise here

#85

Trinity Large Preview

Arcee AI Release: 2026-01-27 Tested on: 2026-04-23 10:54 arcee-ai/trinity-large-preview::none

Score

5.3

Consistency

9.6

Reliability

N/A

Total Cost (Current Price)

$0.000

Total Output Tokens

1,985

Total Input Tokens

0

Input Price

$0.150 / 1M

Output Price

$0.450 / 1M

Tests Correct

Wrong Tests: 13

Attempt pass rate: 29.6%

Flaky tests

1

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

5.07s

Response Time (max): 39.47s

Response Time (total): 91.23s

Wrong answer: 11 Did not follow instructions: 2

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-05-22 00:42 Suite changed 4.8 10.0 $0.001 Compare
2026-05-08 15:30 Suite changed 4.8 10.0 $0.001 Compare
2026-04-23 10:54 First recorded run 5.3 N/A $0.000 Current run

Run comparison

RunScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-04-23 10:54 · First recorded run5.39.6N/A5/1811,9850$0.0005.07s
2026-05-22 00:42 · Suite changed4.88.910.04/1932,1900$0.0013.03s
Difference+0.6+0.70-2-2050-$0.001+2037ms

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Charts

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

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Trinity Large PreviewnonevsMiniMax M2.7mediumTrinity Large PreviewnonevsDeepSeek V3.2noneTrinity Large PreviewnonevsGrok 4.20noneTrinity Large PreviewnonevsQwen3.5-122B-A10BnoneTrinity Large Previewnonevsgpt-oss-120bnoneFree AvailableTrinity Large PreviewnonevsGLM 5 TurbononeTrinity Large PreviewnonevsGemini 3 Flash PreviewmediumTrinity Large PreviewnonevsGemini 3.5 FlashhighTrinity Large PreviewnonevsRing-2.6-1TmediumTrinity Large PreviewnonevsGemini 3.5 Flashlow

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 3.0 10.0
Coding 6.3 10.0
Combined 3.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 4.4 9.9
Instructions following 4.1 6.7
Puzzle Solving 5.4 10.0
Tool Calling 10.0 10.0

Compared models