#276 Trinity Large Preview
none
No endpoints found for arcee-ai/trinity-large-preview:free.
- Cost
- $0.000
- Time
- 0.0s
- Tokens
- 0 tok
Arcee AI
Release: 2026-01-27
Tested on: 2026-06-04 14:30
arcee-ai/trinity-large-preview::none
398B total (13B active)MoEOpen source Summary
Trinity Large Preview scores 4.8 on AI BENCHY and ranks #276. It has 10.0 reliability, a 21.2% pass rate, $0.008 total cost, and 2.98s average response time.
What makes Trinity Large Preview unique: It stands out most in Data parsing and extraction, where it ranks #1, while Instructions following is its weakest area at #13.
Model facts
Researched on 2026-08-12
- Parameters
- 398B total (13B active)
- Architecture
- MoE
- Availability
- Open source
- License
- Apache-2.0
4.8
Consistency
8.9
10.0
Total Output Tokens
2,169
Total Input Tokens
29,828
Input Price
$0.243 / 1M
Output Price
$0.243 / 1M
Flaky tests
2
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-06-04 14:30 New test added | 4.8 | 10.0 | $0.008 ↑ | Current run | |
| 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 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-06-04 14:30 · Current run | 63/66 attempts | 4.8 | 8.9 | 10.0 | 4/21 | 2 | 2,169 | 29,828 | $0.008 | 2.98s |
| 2026-05-08 15:30 · Suite changed | 57/57 attempts | 4.8 | 8.9 | 10.0 | 4/19 | 3 | 2,190 | 0 | $0.001 | 3.03s |
| Difference | — | 0.0 | 0.0 | 0.0 | 0 | -1 | -21 | +29828 | +$0.008 | -54ms |
Benchmark coverage differs: 63/63 attempts (Target: 3 repeats per test) versus 57/57 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.
These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.
Price History
Historical pricing data for this model from OpenRouter.
| Date | Input Price | Output Price |
|---|---|---|
| 2026-06-04 15:40 | $0.243 / 1M | $0.243 / 1M |
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Trinity Large PreviewnonevsGLM 4.7 FlashnoneTrinity Large PreviewnonevsCobuddymediumTrinity Large PreviewnonevsKAT-Coder-Air V2.5noneTrinity Large PreviewnonevsMercury 2noneTrinity Large PreviewnonevsTrinity Large ThinkinghighTrinity Large PreviewnonevsGranite 4.2 8BhighTrinity Large PreviewnonevsGPT-5.4 NanononeTrinity Large PreviewnonevsQwen3 Coder NextmediumTrinity Large PreviewnonevsNemotron 3.5 LightninglowFree AvailableTrinity Large PreviewnonevsMiniMax M2.5medium
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 3.1 | 10.0 | |
| Coding | 3.7 | 7.7 | |
| Combined | 1.5 | 5.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 4.5 | 10.0 | |
| Instructions following | 3.5 | 10.0 | |
| Puzzle Solving | 3.6 | 7.7 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |