NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-12-01KKHZ3CK4GCZWFRPP925P3EQC
Run Details
Model:
Grok 4.20 (Beta)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.1s
Cost:
$0.001664
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
25.9628%
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 adjusted her fake clown wig and stared at the colorful invitation. “Bill, this is insane. We’re robbing a kiddie party? For what, a mountain of Polly Pockets and half-eaten cake?” Bill grinned, rubbing his hands together. “Exactly, Mol. Think about it. Twenty screaming six-year-olds, distracted by a magician who can’t even pull a rabbit out of his hat. Parents half-drunk on cheap punch. The presents are just sitting there under a giant inflatable unicorn. It’s practically begging to be liberated.” “We’re not liberating toys, you walnut. We’re committing felony larceny at a bounce house,” Molly hissed. “What if some kid starts crying? I can’t handle tiny tears. They’re like emotional kryptonite.” “Relax. We go in as the entertainment. I’m the world’s worst balloon animal guy. You’re the face-painter who only knows how to draw sad potatoes. While the rugrats are fighting over who gets the purple giraffe, we bag the gifts and vanish out the back like pros.” Molly sighed. “If we get caught, I’m blaming your midlife crisis.” Bill winked. “Fair enough. Now help me practice my squeaky voice. Kids love that.”
created_at
"2026-03-12T21:26:33.832Z"
3/12/2026, 9:26:33 PM
model
"x-ai/grok-4.20-beta-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
404
moderation_latency
(null)
generation_time
1993
tokens_prompt
77
tokens_completion
309
native_tokens_prompt
182
native_tokens_completion
255
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
0.0016636
router
(null)
provider_responses
0
endpoint_id
"33f49f24-a0de-4dcf-872d-ca514e83fbae"
id
"cd84f844-a651-eda9-e3b9-73b170a01837"
is_byok
false
latency
403
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-1773350793-DuWkx9NtBeIwqUm1v0to"
upstream_id
"cd84f844-a651-eda9-e3b9-73b170a01837"
total_cost
0.0016636
cache_discount
0.0002304
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
51.93%
Matches word count
n/a
neededClean
false
words
184
0.00%
Dialogue to Total Word Ratio
Ratio: 87.30%, Deviation: 37.30%
neededClean
false
wordsTotal
189
wordsDialogue
165
25.9628%