NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-17-01KHNFTHFMPMW6RARSWKV8HSC4
Run Details
Model:
Arcee AI: Trinity Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.8s
Cost:
$0.000120
Provider:
Clarifai
Evaluation summary
Score
Evaluator
Details Link
0.00%
Matches word count
(details)
54.55%
Dialogue to Total Word Ratio
(details)
27.2727%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 slammed her fist on thetable. "This is it, Bill! The jackpot! That billionaire's kid's birthday bash! All those shiny presents under the tree! We hit it tonight!" Bill adjusted his glasses, peering at the detailed map spread out. "Molly, we've discussed this. A children's party? The security is... enthusiastic. There's a clown with a whistle that could shatter glass, and the parents are like a pack of guard dogs. Not to mention the... *noise*." Molly waved a dismissive hand. "Noise? We're thieves, Bill! We thrive on chaos! Think of the loot! Toys! Gadgets! Maybe even that giant teddy bear that looks suspiciously like a vault! We sneak in, grab the presents, and vanish before the cake hits the floor!" Bill sighed, rubbing his temples. "The presents are *under* the tree, Molly. The tree is *inside* the house. The house has walls. Walls have doors. Doors have locks. Locks have... well, locks. And the parents are *outside* the house, but they're *everywhere*. They see everything. They know everything. They have... *eyes*." Molly grinned, already picturing the haul. "Eyes? We'll be invisible! We'll wear those ninja suits from the thrift store! Black as the night! Silent as... well, as thieves! We move like shadows, Bill! Shadows that steal!" Bill pointed at the map. "The shadows have to navigate the backyard. The backyard has a... *fence*. A fence with... *nails*. And a... *dog*. A very large, very loud dog. A dog that barks at... *everything*. Including the wind." Molly's eyes sparkled with reckless determination. "We'll distract the dog! With... a squeaky toy! Or maybe... a steak! We're professionals, Bill! We improvise! We're Molly and Bill! The Unstoppable Present Pirates!" Bill looked at the map again, then at Molly's beaming face. "Right. Pirates. Okay. Plan B involves... very small windows. And... very quiet shoes. And... maybe a very large bribe for the dog. But only if it's... *edible*." Molly grabbed Bill's arm, pulling him towards the door. "No time for details! The party starts in... *two hours*! Let's go steal some childhood joy!"
created_at
"2026-02-17T09:45:14.621919+00:00"
2/17/2026, 9:45:14 AM
model
"arcee-ai/trinity-mini-20251201"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
67
moderation_latency
(null)
generation_time
4770
tokens_prompt
77
tokens_completion
908
native_tokens_prompt
70
native_tokens_completion
781
native_tokens_completion_images
(null)
native_tokens_reasoning
372
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
0.0001203
router
(null)
provider_responses
0
id
"570ee6d905e549608ca7025b2744d0b2"
status
200
is_byok
false
latency
67
endpoint_id
"73d82c49-90ae-4223-a860-83ed0810821f"
provider_name
"Clarifai"
model_permaslug
"arcee-ai/trinity-mini-20251201"
api_type
"completions"
id
"gen-1771321509-SAIxHYShQBGqelMWzNgZ"
upstream_id
"570ee6d905e549608ca7025b2744d0b2"
total_cost
0.0001203
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
340
54.55%
Dialogue to Total Word Ratio
Ratio: 81.18%, Deviation: 8.82%
neededClean
false
wordsTotal
340
wordsDialogue
276
27.2727%