Navigate
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com

Trinity Large Preview (default) vs Nemotron 3 Super

The average score is effectively tied at 4.4 vs 4.5. Trinity Large Preview (default) has the lower benchmark cost at $0.008 vs $0.016. Trinity Large Preview (default) is faster at 2.83s vs 7.11s, with pass rates of 20.3% vs 27.5%.

Last updated at: 2026-10-07

Compared models

Rank
#349
Total Output Tokens
2,169
Response Time (avg)
2.83s
Total Cost
$0.008
Rank
#347
Total Output Tokens
9,074
Response Time (avg)
7.11s
Total Cost
$0.016
Recommended model Trinity Large Preview (default)

It has the best score here (4.4), while costing about 2.0x less than Nemotron 3 Super.

Detailed comparison

Metric Trinity Large Preview Trinity Large Preview default Release: 2026-01-27 Free Available Nemotron 3 Super Nemotron 3 Super none Release: 2026-03-11 Free Available
Score 4.4 4.5
Rank #349 #347
Reliability 10.0 9.5
Consistency 9.0 8.9
Attempts 66/69 69/69
Tests Correct
Attempt pass rate 20.3% 27.5%
Flaky tests 2 3
Total Runs 66 69
Cost per result 0.017 0.034
Total Cost $0.008 $0.016
Input Price $0.243 / 1M $0.080 / 1M
Output Price $0.243 / 1M $0.450 / 1M
Cache Read Price N/A N/A
Cache Write Price N/A N/A
Total Input Tokens 29,828 146,361
Output Tokens 2,169 9,073
Reasoning Tokens 0 1
Response Time (avg) 2.83s 7.11s
Response Time (max) 14.34s 30.51s
Response Time (total) 56.65s 163.46s
Parameters 398B total (13B active) 120B total (12B active)
Availability Open source Weights available

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Model generation showcase

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#349 Trinity Large Preview

default
No endpoints found for arcee-ai/trinity-large-preview:free.
Cost
$0.000
Time
0.0s
Tokens
0 tok

#347 Nemotron 3 Super

none
Cost
$0.000
Time
137.8s
Tokens
2,447 tok

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
Trinity Large Preview 3.7 7.7 11.1% 1 14.34s 738 397 0
Nemotron 3 Super 3.3 7.2 11.1% 1 2.64s 7,627 571 0

Quick Compare

Switch Comparison Pair