NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY7XV5XMWDAPTC5JHRNA25Z
Run Details
Model:
Grok 4.1 Fast
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
6.8s
Cost:
$0.000300
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
6.09%
Matches word count
(details)
57.22%
Dialogue to Total Word Ratio
(details)
31.6542%
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 leaned over the grimy kitchen table, jabbing a finger at a crayon-scribbled map. "Listen up, Bill. The Johnsons' backyard bash tomorrow—twenty snot-nosed rugrats, pile of presents taller than me. We snag 'em all." Bill scratched his stubbled chin, eyes lighting up. "Presents? Like bikes and Barbies? Sweet score! How we crashin' without the kiddie cops wailin'?" "Disguises, dummy. I'm the balloon lady—big red wig, squeaky nose. You? Party magician. Black cape, top hat stuffed with gift bags." Bill grinned maniacally. "Abracadabra, presents vanish! But the cake? We grab that too?" Molly snorted. "Cake's for diversion. Smear it on the birthday boy, chaos erupts. We scoop loot into my van disguised as the pony ride trailer." "What if pony kicks us? Or some mini-Sherlock spots the swag?" "I'll trip the brat with my clown shoe. You sleight-of-hand the big teddy. In and out in ten—rich off Elmo dolls by midnight!" Bill fist-pumped. "To heisting the kiddie jackpot!" Molly smirked. "Shh, or we'll be stealin' coal from Santa next."
created_at
"2026-02-20T19:20:18.885Z"
2/20/2026, 7:20:18 PM
model
"x-ai/grok-4.1-fast"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
617
moderation_latency
(null)
generation_time
6649
tokens_prompt
77
tokens_completion
344
native_tokens_prompt
216
native_tokens_completion
559
native_tokens_completion_images
0
native_tokens_reasoning
289
native_tokens_cached
154
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
0.0002996
router
(null)
provider_responses
0
endpoint_id
"9821aa0e-dce3-4c27-9716-161359123d0b"
id
"85eb7161-f8b9-9def-3f07-223bfe38273b"
is_byok
false
latency
401
model_permaslug
"x-ai/grok-4.1-fast"
provider_name
"xAI"
status
200
api_type
"completions"
id
"gen-1771615218-cQGRnyiSGr34uPvXIVwx"
upstream_id
"85eb7161-f8b9-9def-3f07-223bfe38273b"
total_cost
0.0002996
cache_discount
0.0000231
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
6.09%
Matches word count
n/a
neededClean
false
words
177
57.22%
Dialogue to Total Word Ratio
Ratio: 81.36%, Deviation: 8.64%
neededClean
false
wordsTotal
177
wordsDialogue
144
31.6542%