NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-12-01KKHZ5P0BKXGAP418AASNTEK9
Run Details
Model:
Grok 4.20 (Beta)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.4s
Cost:
$0.001934
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 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 crouched behind the hedge, peering at the bouncy castle pulsing with shrieking six-year-olds. “We’re really doing this?” Molly whispered. “Stealing birthday presents from toddlers?” Bill grinned. “Think of it as redistribution of wealth. Those kids get new toys every week. My niece got socks.” “Socks aren’t presents, Bill. They’re parenting mistakes.” “Exactly. We’re correcting the system. In and out, two minutes tops. I distract with the fake magician act, you grab the gift table.” Molly rolled her eyes. “Your fake magician act is just yelling ‘abracadabra’ while dropping cards. Last time a toddler punched you.” “That was a love tap. Besides, I’ve upgraded. I now have a cape. Capes scream legitimacy.” “Legitimacy to who? The PTA?” “Look, we hit the presents, swap the big boxes with empty ones wrapped in identical paper, and vanish before the candles are lit. Easy.” “Easy? There’s a clown in there, Bill. Clowns have instincts.” “Clowns have baggy pants and low self-esteem. I can take a clown.” Molly sighed. “If we get caught I’m telling the cops you made me do it.” “Fine. But if we pull this off, we split the haul fifty-fifty. Even the Ninja Turtle tote bag.” “Deal. God help us.”
created_at
"2026-03-12T21:27:49.007Z"
3/12/2026, 9:27:49 PM
model
"x-ai/grok-4.20-beta-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
675
moderation_latency
(null)
generation_time
3347
tokens_prompt
77
tokens_completion
361
native_tokens_prompt
182
native_tokens_completion
300
native_tokens_completion_images
0
native_tokens_reasoning
0
native_tokens_cached
128
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
0.0019336
router
(null)
provider_responses
0
endpoint_id
"33f49f24-a0de-4dcf-872d-ca514e83fbae"
id
"29aff36b-c9aa-4d9f-812e-38f904017f65"
is_byok
false
latency
645
model_permaslug
"x-ai/grok-4.20-beta-20260309"
provider_name
"xAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773350869-FufgFCqtw7PKw2DUfnQM"
upstream_id
"29aff36b-c9aa-4d9f-812e-38f904017f65"
total_cost
0.0019336
cache_discount
0.0002304
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: 86.41%, Deviation: 36.41%
neededClean
false
wordsTotal
206
wordsDialogue
178
49.9920%