NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY7GX9CRH5FEPA9AYWES1N1
Run Details
Model:
Grok 4 Fast
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4.2s
Cost:
$0.000261
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
46.8248%
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 hunched over the rickety kitchen table, blueprints of the suburban mansion spread out like a treasure map to piñata paradise. Bill paced, twirling a fake mustache he'd stolen from a costume shop—ironic, since they were targeting a kid's birthday bash. "Look, Bill, it's foolproof," Molly whispered, jabbing a finger at the diagram. "We pose as clowns. Slip in during the cake smash, grab the gift pile while the rugrats are distracted by balloon animals." Bill snorted, nearly tripping over his untied shoelaces. "Clowns? I can't juggle worth a damn. Last time I tried, I beaned myself with a rubber chicken." "Exactly! Play the bumbling fool—kids love that. We'll stuff the presents into oversized polka-dot pants. Out the back door in five minutes flat." He leaned in, eyes gleaming. "And the take? Designer bikes, video games—easy ten grand resale." Molly grinned wickedly. "More like twenty. But watch for the birthday boy; he's got a ninja phase." Bill chuckled. "Ninja toddler? Bring it. We're the dynamic duo of dastardly delight." As they high-fived, a stray blueprint fluttered to the floor, revealing the party's theme: Superhero Safari. Molly groaned. "Great, now we need capes and toy rifles?" Bill winked. "Adapt and steal, partner. Adapt and steal."
created_at
"2026-02-20T19:13:15.394Z"
2/20/2026, 7:13:15 PM
model
"x-ai/grok-4-fast"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1833
moderation_latency
(null)
generation_time
3623
tokens_prompt
77
tokens_completion
335
native_tokens_prompt
216
native_tokens_completion
482
native_tokens_completion_images
0
native_tokens_reasoning
187
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
0.0002611
router
(null)
provider_responses
0
endpoint_id
"c9586d9d-97ff-40ca-ae94-22504d6f9b7e"
id
"54aaeee0-7028-6670-7eba-9a1260df75db"
is_byok
false
latency
497
model_permaslug
"x-ai/grok-4-fast"
provider_name
"xAI"
status
200
api_type
"completions"
id
"gen-1771614795-EIICPORL7YXchwC9hg1c"
upstream_id
"54aaeee0-7028-6670-7eba-9a1260df75db"
total_cost
0.0002611
cache_discount
0.0000231
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
209
0.00%
Dialogue to Total Word Ratio
Ratio: 57.42%, Deviation: 47.42%
neededClean
false
wordsTotal
209
wordsDialogue
120
46.8248%