NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYAWZ5WSKCKYMTGYFH5Q1JN
Run Details
Model:
Grok 4.1 Fast
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.8s
Cost:
$0.000393
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9920%
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 and Bill crouched in the shadows of their rusty van, binoculars trained on the riotous children's party across the street. Streamers tangled like festive spiderwebs, and a horde of sugar-fueled gremlins rampaged around a bouncy castle shaped like a dinosaur. The gift table groaned under a mountain of shiny-wrapped loot: bikes, dolls, gadgets galore. Molly, her face smeared with greasepaint camouflage, unrolled a napkin sketch of the chaos. "Phase one: crash as balloon animals. Kids'll swarm us." Bill nodded, stuffing fake noses into his pockets. "Then piñata whack—grab presents mid-candy storm." She traced the escape route with a candy-striped pencil. "Parents distracted by face-painting clown—me. You rig the cake with itching powder. Instant itch-fest." Bill snorted, envisioning the pandemonium. "Genius. But the birthday tyrant's got a guard dog: fluffy pony." "Pony treats in my bra," Molly winked. "Lure and load the van." He sketched a getaway diagram on a pizza box. "Two minutes max. We're ghosts by cake-smash." They clinked root beer cans, eyes gleaming with larcenous glee. The heist promised slapstick glory: dodging toddlers, outwitting soccer moms, vanishing with a haul worth a candy empire. Innocence was about to get fleeced.
created_at
"2026-02-20T20:12:15.943Z"
2/20/2026, 8:12:15 PM
model
"x-ai/grok-4.1-fast"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
451
moderation_latency
(null)
generation_time
9689
tokens_prompt
77
tokens_completion
400
native_tokens_prompt
216
native_tokens_completion
746
native_tokens_completion_images
0
native_tokens_reasoning
459
native_tokens_cached
153
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
0.00039325
router
(null)
provider_responses
0
endpoint_id
"9821aa0e-dce3-4c27-9716-161359123d0b"
id
"040c33da-79a9-6150-c5a9-8156d715496e"
is_byok
false
latency
173
model_permaslug
"x-ai/grok-4.1-fast"
provider_name
"xAI"
status
200
api_type
"completions"
id
"gen-1771618335-WBgBUBbvWgx2YInh1Zeo"
upstream_id
"040c33da-79a9-6150-c5a9-8156d715496e"
total_cost
0.00039325
cache_discount
0.00002295
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
0.00%
Dialogue to Total Word Ratio
Ratio: 31.19%, Deviation: 21.19%
neededClean
false
wordsTotal
202
wordsDialogue
63
49.9920%