NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY9GED00CB8ZP6THGDTM4SY
Run Details
Model:
Grok 4
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
18.6s
Cost:
$0.008035
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.3562%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 adjusted her oversized clown wig in the dim light of their dingy van, parked just outside the bustling suburban backyard. Balloons bobbed like drunken sentinels, and the air thrummed with the chaotic squeals of sugar-fueled kids. Bill, her partner in crime, fiddled with a comically large fake nose, his face painted in what he claimed was "stealth clown camouflage." "This is foolproof," Bill whispered, peering through binoculars at the pile of glittering presents under a rainbow piƱata. "We blend in as entertainers, grab the loot during the cake chaos, and vanish like ghosts with gift bags." Molly snorted, eyeing the itinerary she'd swiped from the mailbox. "You're an idiot. The party's got a bouncy castle guarded by a pack of hyper toddlers. One wrong step, and we're buried in diapers." Bill grinned, adjusting his polka-dot bowtie. "Trust me, Mol. I've got the getaway tricycle ready." She rolled her eyes. "Fine, but if we get caught, you're the one explaining to the cops why we're dressed like discount Ronald McDonalds." As they slipped out, a stray balloon popped, sending them both diving behind a hedge. The heist was on, ridiculous as ever.
created_at
"2026-02-20T19:47:56.974Z"
2/20/2026, 7:47:56 PM
model
"x-ai/grok-4-07-09"
4/7/2009, 12:00:00 AM
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
7603
moderation_latency
(null)
generation_time
18505
tokens_prompt
77
tokens_completion
301
native_tokens_prompt
744
native_tokens_completion
489
native_tokens_completion_images
0
native_tokens_reasoning
233
native_tokens_cached
681
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
"completed"
usage
0.00803475
router
(null)
provider_responses
0
endpoint_id
"d40bef9d-6936-4c57-9749-bf7399de4a77"
id
"5deeb7d7-4819-9be7-b5f1-6df1660b0a6a"
is_byok
false
latency
794
model_permaslug
"x-ai/grok-4-07-09"
4/7/2009, 12:00:00 AM
provider_name
"xAI"
status
200
api_type
"completions"
id
"gen-1771616876-s3fNBRqt8oF542oRPbnn"
upstream_id
"5deeb7d7-4819-9be7-b5f1-6df1660b0a6a"
total_cost
0.00803475
cache_discount
0.00153225
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
194
0.00%
Dialogue to Total Word Ratio
Ratio: 40.21%, Deviation: 30.21%
neededClean
false
wordsTotal
194
wordsDialogue
78
49.3562%