NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHYAW1WSGXZT3RP87WGB5M1S
Run Details
Model:
Grok 4.1 Fast
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.0s
Cost:
$0.000322
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
62.34%
Dialogue to Total Word Ratio
(details)
81.1675%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 huddled in their dimly lit van parked across from the suburban McMansion, binoculars trained on the backyard where balloons bobbed and squealing kids swarmed a mountain of gift-wrapped loot. Blueprints of the house lay spread across the dashboard, annotated with crayon scribbles. "Bill, it's perfect," Molly whispered, eyes gleaming. "We crash as the 'Magic Unicorn Entertainers.' I got the costumes—hooves and all." Bill snorted, adjusting his fake mustache. "Hooves? How we gonna run with sacks of Barbies and Xboxen? Nah, we spike the punch with sleepy-time juice. Kids conk out, parents tipsy, we grab and dash." Molly slapped his arm. "Genius! But what about that bouncy castle? It's a fortress of snot-nosed guards." "Piñata ploy!" Bill cackled. "I swing the stick, you rig it with candy explosives. Boom—distraction city. Presents ours in sixty seconds flat." "Explosives? You're nuts," Molly laughed. "Fine, but if Clowny Carl shows, you're decoy. Last time you juggled, we almost got pinched." Bill winked. "Deal. At 3 PM sharp, Operation Present Heist launches. Richest score since that Easter Bunny gig." As laughter echoed, a kid spotted the van and waved. Molly floored it, hearts pounding with glee.
created_at
"2026-02-20T20:11:45.957Z"
2/20/2026, 8:11:45 PM
model
"x-ai/grok-4.1-fast"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
346
moderation_latency
(null)
generation_time
7877
tokens_prompt
77
tokens_completion
391
native_tokens_prompt
216
native_tokens_completion
603
native_tokens_completion_images
0
native_tokens_reasoning
312
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
0.00032175
router
(null)
provider_responses
0
endpoint_id
"9821aa0e-dce3-4c27-9716-161359123d0b"
id
"b3f42cfa-ad71-ed52-3eac-9a4a4774d96a"
is_byok
false
latency
68
model_permaslug
"x-ai/grok-4.1-fast"
provider_name
"xAI"
status
200
api_type
"completions"
id
"gen-1771618305-LT2ca7FSiSnosPiNH8m6"
upstream_id
"b3f42cfa-ad71-ed52-3eac-9a4a4774d96a"
total_cost
0.00032175
cache_discount
0.00002295
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
62.34%
Dialogue to Total Word Ratio
Ratio: 58.29%, Deviation: 8.29%
neededClean
false
wordsTotal
199
wordsDialogue
116
81.1675%