NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY89GYFV4KR0VJ05PEWRJPH
Run Details
Model:
Grok 4
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
18.5s
Cost:
$0.008557
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
50.0000%
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 fake mustache in the dim light of their van, parked two blocks from the bustling suburban house. Balloons bobbed in the yard, and the distant squeals of children mixed with a clown's honking horn. Bill, dressed as an oversized teddy bear, peered through binoculars, his furry paws fumbling. "This is genius, Molly," Bill whispered, his voice muffled by the costume. "Kids' parties are goldmines—presents stacked like pyramids!" Molly smirked, sketching a crude map on a napkin. "Yeah, but we gotta time it right. Wait for the piñata smash—total chaos. You distract the clown, I'll swipe the gift table." Bill chuckled. "Distract? How? Challenge him to a balloon animal duel?" "Exactly! Make it epic. I'll be in and out like a ghost with wrapping paper." Bill nodded, eyes gleaming. "And the getaway? Kiddie pool floaties as decoys?" Molly laughed. "Brilliant. But remember, no touching the cake—too messy." As the party music swelled, they high-fived awkwardly through costumes. Bill grinned. "Operation Birthday Bandit is a go!" Molly winked. "Let's make these kids' wishes come true—for us." They slipped out, hearts pounding with mischievous glee, ready to turn the festivities into their personal treasure hunt.
created_at
"2026-02-20T19:26:41.628Z"
2/20/2026, 7:26:41 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
7504
moderation_latency
(null)
generation_time
18432
tokens_prompt
77
tokens_completion
328
native_tokens_prompt
744
native_tokens_completion
524
native_tokens_completion_images
0
native_tokens_reasoning
249
native_tokens_cached
682
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
0.0085575
router
(null)
provider_responses
0
endpoint_id
"d40bef9d-6936-4c57-9749-bf7399de4a77"
id
"217671a7-3c97-2ac2-5253-f7bd899b7696"
is_byok
false
latency
115
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-1771615601-aNi8Jt5DxDGu8s09WJpt"
upstream_id
"217671a7-3c97-2ac2-5253-f7bd899b7696"
total_cost
0.0085575
cache_discount
0.0015345
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
0.00%
Dialogue to Total Word Ratio
Ratio: 45.50%, Deviation: 35.50%
neededClean
false
wordsTotal
200
wordsDialogue
91
50.0000%