NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-01-01KQHRKB92D1997EW37YHXC7D5
Run Details
Model:
Grok 4.20
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.9s
Cost:
$0.000753
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
66.3873%
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
“Bill, you’re joking. A kiddie party? We’re not stealing candy from babies.” “It’s not candy, Molly—it’s presents. Twenty screaming moppets, one giant pile of wrapped glory. We’ll be in and out before the piñata hits the floor.” “You want us to crash a bounce house in ski masks? That’s not a heist, that’s a felony with frosting.” “No masks. We’ll wear the giant mascot costumes from the supply closet. I’m the dancing dinosaur, you’re the depressed unicorn. Kids’ll think we’re hired entertainment.” “I refuse to be the depressed unicorn, Bill.” “Fine, you’re the sparkly T-Rex. Look, we drop in during musical chairs, I cut the lights, you wheel the gift table out like it’s on casters. We’ll have it in the van before they finish ‘Happy Birthday.’” “What about the parents? They’re not exactly blind.” “Parents are glued to their phones filming little Timmy. By the time they look up we’ll be two blocks away arguing over who gets the Lego Star Destroyer.” “I still say this is the dumbest idea you’ve ever had.” “Dumber than the time we tried to rob the police auction?” “…Start the van, you giant lizard.”
created_at
"2026-05-01T12:35:44.038Z"
5/1/2026, 12:35:44 PM
model
"x-ai/grok-4.20-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
413
moderation_latency
(null)
generation_time
4822
tokens_prompt
77
tokens_completion
329
native_tokens_prompt
182
native_tokens_completion
264
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
0.0007531
router
(null)
provider_responses
0
endpoint_id
"3ecee37f-b217-4093-87fb-aaf0afe307af"
id
"09a4da25-f871-be88-fc66-31670c1a6b49"
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-1777638944-0tlrn5RAvSmaDJK2kn1B"
session_id
(null)
api_type
"completions"
id
"gen-1777638944-hVFEZruh5yEAykFJ4jIE"
upstream_id
"09a4da25-f871-be88-fc66-31670c1a6b49"
total_cost
0.0007531
cache_discount
0.0001344
upstream_inference_cost
0
provider_name
"xAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
192
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
192
wordsDialogue
192
66.3873%