NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHNF6ACRRGC2SVFA4J7R8HV6
Run Details
Model:
Arcee AI: Trinity Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.3s
Cost:
$0.000104
Provider:
Clarifai
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
Molly leaned against the fence, hereyes fixed on the brightly colored balloons bobbing above the backyard. "Look at that," she murmured, a wicked grin spreading across her face. "A whole treasure trove of shiny things, just sitting there." Bill adjusted his glasses, peering through his binoculars. "Molly, it's a children's birthday party. The 'treasure' is wrapped in wrapping paper and filled with cheap plastic toys. The parents are probably still paying off the cake." "Details, Bill," Molly scoffed. "Think of the potential! Those Lego sets, the new bikes, the gaming consoles... pure gold! And the parents will be too busy chasing toddlers to notice a couple of... 'party planners' sneaking in." Bill sighed, rubbing his temples. "Molly, the security is a three-year-old with a juice box. The 'security system' is a crying baby monitor. The 'guards' are exhausted parents trying to keep sugar-fueled chaos contained." Molly pointed at the cake. "Exactly! They're all hopped up on sugar and frosting. A little distraction, a quick grab, and we're out before the sugar crash hits. It's a perfect heist!" Bill hesitated, then lowered the binoculars. "A perfect heist? Molly, we'd need a getaway vehicle that can outrun a toddler on a tricycle. And what about the... emotional attachment? Stealing from kids? That's crossing a line, even for us." Molly shrugged, already moving towards the gate. "Emotional attachment? Please. It's just stuff. Stuff that isn't nailed down. And we'll replace it with... better stuff. Trust me, Bill. This is our biggest score yet." She slipped through the gate before he could argue further.
created_at
"2026-02-17T09:34:10.812085+00:00"
2/17/2026, 9:34:10 AM
model
"arcee-ai/trinity-mini-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
74
moderation_latency
(null)
generation_time
3120
tokens_prompt
77
tokens_completion
810
native_tokens_prompt
70
native_tokens_completion
674
native_tokens_completion_images
(null)
native_tokens_reasoning
390
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.00010425
router
(null)
provider_responses
0
id
"59562a70de954ad8b853e14cb5ae434f"
status
200
is_byok
false
latency
74
endpoint_id
"73d82c49-90ae-4223-a860-83ed0810821f"
provider_name
"Clarifai"
model_permaslug
"arcee-ai/trinity-mini-20251201"
api_type
"completions"
id
"gen-1771320846-j2HCoWAy2QmWTcuuqFpl"
upstream_id
"59562a70de954ad8b853e14cb5ae434f"
total_cost
0.00010425
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Clarifai"
Evaluation details
Result
Evaluator
Details
Meta Data
0.00%
Matches word count
n/a
neededClean
false
words
263
0.00%
Dialogue to Total Word Ratio
Ratio: 74.14%, Deviation: 24.14%
neededClean
false
wordsTotal
263
wordsDialogue
195
0.0000%