NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYBB2XF2VBG33VSCAH28DXX
Run Details
Model:
Grok 4 Fast
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.6s
Cost:
$0.000249
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
11.64%
Dialogue to Total Word Ratio
(details)
55.8174%
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 hunched over the kitchen table, blueprints of the suburban backyard spread out like a treasure map. Bill paced, twirling a fake mustache that kept slipping off his lip. "Listen, Bill, it's genius," Molly whispered, eyes gleaming. "Kids' birthday bash at the Johnsons'. Balloons, cake, and a mountain of presents under that clown piñata. We slip in as caterers—I've got the van rigged with balloon animals for cover." Bill snorted, adjusting his mustache. "Caterers? With my allergies? One whiff of hot dogs and I'm sneezing glitter. What if the kids spot us? Those rugrats are like tiny detectives." "Exactly! We blame the clown. 'Hey, kids, the funny man took the toys!' Then we dash out the back with the loot. Load the presents into gift bags, call it a 'surprise giveaway' for our next gig." Bill stopped pacing, grinning. "Okay, but we need diversions. You handle the face painting—turn 'em into zombies. I'll rig the bounce house to deflate mid-jump. Chaos city!" Molly laughed. "Perfect. In and out in ten minutes. Richest haul since that pet store fiasco. No more ramen for us!" "Deal. But if I get pied in the face again, you're driving getaway."
created_at
"2026-02-20T20:19:58.521Z"
2/20/2026, 8:19:58 PM
model
"x-ai/grok-4-fast"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1079
moderation_latency
(null)
generation_time
2463
tokens_prompt
77
tokens_completion
303
native_tokens_prompt
216
native_tokens_completion
477
native_tokens_completion_images
0
native_tokens_reasoning
204
native_tokens_cached
215
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
0.00024945
router
(null)
provider_responses
0
endpoint_id
"c9586d9d-97ff-40ca-ae94-22504d6f9b7e"
id
"cf4640fb-1b55-9c50-a693-f916810444b4"
is_byok
false
latency
97
model_permaslug
"x-ai/grok-4-fast"
provider_name
"xAI"
status
200
api_type
"completions"
id
"gen-1771618798-dCaQFN6MrTXgA1iL8REK"
upstream_id
"cf4640fb-1b55-9c50-a693-f916810444b4"
total_cost
0.00024945
cache_discount
0.00003225
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
199
11.64%
Dialogue to Total Word Ratio
Ratio: 77.89%, Deviation: 12.11%
neededClean
false
wordsTotal
199
wordsDialogue
155
55.8174%