NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-01-01KQHRQCH952093KM63RGXAD40
Run Details
Model:
Grok 4.20
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.5s
Cost:
$0.000793
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.2661%
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
“We’re really doing this, Bill? Crashing a kiddie party for some plastic trucks and half-eaten cake?” “Presents, Molly. Whole table of them. Little Timmy’s getting a bicycle. We’re getting a bicycle. Think of the resale.” “You want me to shimmy down the chimney in a Mrs. Claus costume while twenty sugar-high goblins scream?” “Better than the vent again. Last time you got stuck and I had to pretend I was the piñata.” “I still have candy in my bra. Focus. We hit at peak present-opening, right after the magician leaves.” “Magician’s our inside man. He’s gonna ‘accidentally’ set off the smoke bombs. Chaos equals cover.” “Smoke bombs at a children’s party? You monster.” “Monster with a getaway van full of stolen Xboxes, love. You in or what?” “Fine, but I’m wearing the dinosaur costume. Nobody suspects the T-Rex.” “Deal. Just don’t eat the birthday boy this time.” “That was one time and he tasted like regret. We grab the gifts, bolt through the balloon arch, and vanish before the parents finish their sangria.” “Beautiful. Now help me glue googly eyes on these walkie-talkies. They’re our ‘party favors.’” “You’re an evil genius.” “Thank you. Pass the glitter.”
created_at
"2026-05-01T12:37:56.398Z"
5/1/2026, 12:37:56 PM
model
"x-ai/grok-4.20-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
385
moderation_latency
(null)
generation_time
4430
tokens_prompt
77
tokens_completion
348
native_tokens_prompt
182
native_tokens_completion
280
native_tokens_completion_images
(null)
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)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.0007931
router
(null)
provider_responses
0
endpoint_id
"3ecee37f-b217-4093-87fb-aaf0afe307af"
id
"57495699-8b23-9be4-8140-45f940ea67f6"
is_byok
false
latency
88
model_permaslug
"x-ai/grok-4.20-20260309"
provider_name
"xAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777639076-MFql26atmTrcwg4T4zLJ"
session_id
(null)
api_type
"completions"
id
"gen-1777639076-vgShkTuxuHIXQpICyozw"
upstream_id
"57495699-8b23-9be4-8140-45f940ea67f6"
total_cost
0.0007931
cache_discount
0.0001344
upstream_inference_cost
0
provider_name
"xAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
200
wordsDialogue
200
68.2661%