NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-20-01KHY8SC4WZR2CYJC72PJ4XAHR
Run Details
Model:
Grok 4.1 Fast
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.3s
Cost:
$0.000306
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
78.54%
Dialogue to Total Word Ratio
(details)
88.6279%
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 and Bill hunched over a crumpled birthday invitation in their smoky hideout, eyes gleaming. "Bill, it's perfect! Rich kid's bash tomorrow—presents stacked like a gold mine!" Molly whispered, grinning wickedly. "Yeah? But snot-nosed rugrats everywhere. One tantrum and we're busted," Bill grumbled, scratching his chin. "Disguises, dummy! We go as the clown duo—me Bozo, you Ding-Dong. Juggle the gifts right out the door." Bill snorted. "Clowns? I look like a depressed walrus in red nose. What if they want balloon animals?" "Practice! Twist a present into a sword—poof, it's ours. Distraction: I spike the punch with sleepy-time juice. Kids nap, we load the van." "Genius, but the birthday cake? Guarded like Fort Knox by that pony mascot." "Pony? We bribe it with carrots laced with laxatives. Chaos ensues, we grab and dash through the bounce house exit." Bill laughed. "Bounce house getaway? We'll look like idiots tumbling with loot!" "Idiots who retire rich. Timing: Cake at two, heist at two-oh-five. No kids, no cops—just us and a mountain of Barbies and Xboxes!" "Deal. World's dumbest heist—stealing from toddlers." They clinked coffee mugs, cackling.
created_at
"2026-02-20T19:35:21.001Z"
2/20/2026, 7:35:21 PM
model
"x-ai/grok-4.1-fast"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1743
moderation_latency
(null)
generation_time
9152
tokens_prompt
77
tokens_completion
380
native_tokens_prompt
216
native_tokens_completion
591
native_tokens_completion_images
0
native_tokens_reasoning
303
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
0.00030645
router
(null)
provider_responses
0
endpoint_id
"9821aa0e-dce3-4c27-9716-161359123d0b"
id
"0b6b3876-12ba-3a7f-1ee1-bdf6cc65576b"
is_byok
false
latency
1341
model_permaslug
"x-ai/grok-4.1-fast"
provider_name
"xAI"
status
200
api_type
"completions"
id
"gen-1771616121-V0pqHpbWkoKE4ZkyH1FO"
upstream_id
"0b6b3876-12ba-3a7f-1ee1-bdf6cc65576b"
total_cost
0.00030645
cache_discount
0.00003225
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
194
78.54%
Dialogue to Total Word Ratio
Ratio: 82.99%, Deviation: 7.01%
neededClean
false
wordsTotal
194
wordsDialogue
161
88.6279%