NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-01-01KQHSNJQ9EZTZSBK03ZEVQ9QE
Run Details
Model:
Grok 4.20
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.2s
Cost:
$0.000875
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
63.6358%
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 children’s party? We’re not stealing lollipops, we’re supposed to be professionals.” “Exactly, Mol. They’ll never suspect us. Think about it—twenty screaming kids, one stressed mum, and a mountain of brightly wrapped presents nobody’s guarding. It’s perfect.” “I swore after the clown museum job I’d never wear face paint again.” “You won’t need it. We go as the hired entertainers. I’m the magician, you’re the balloon artist. We do one trick, spike the punch with sleepy-time juice, and while the little monsters are napping we bag every gift under that giant rainbow banner.” “What if one of them wakes up and wants a pony balloon?” “Then you make him a pony balloon, Molly. A really complicated one that takes ten minutes. I’ll be in the gift corner filling my duffel like Santa on a bender.” “You realize we’re going to hell for this, right?” “Probably, but it’ll be a very festive hell. Look, we split the haul fifty-fifty. Half the kids get socks next year, we get PlayStations and whatever rich parents buy these days. Easy money.” “Fine. But if I get recognized by some tiny birthday tyrant I’m blaming you.” “Fair. Now help me pick a magic word that doesn’t sound dirty. ‘Abracadabra’ is taken.”
created_at
"2026-05-01T12:54:25.775Z"
5/1/2026, 12:54:25 PM
model
"x-ai/grok-4.20-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
411
moderation_latency
(null)
generation_time
5106
tokens_prompt
77
tokens_completion
353
native_tokens_prompt
182
native_tokens_completion
286
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
64
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
0.0008753
router
(null)
provider_responses
0
endpoint_id
"3ecee37f-b217-4093-87fb-aaf0afe307af"
id
"e443a06d-b26d-987d-98fc-72ffb79136e0"
is_byok
false
latency
85
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-1777640065-bnOzMoztl2Uq4D1HejIO"
session_id
(null)
api_type
"completions"
id
"gen-1777640065-1wSaMM4QGNAMnMLegld1"
upstream_id
"e443a06d-b26d-987d-98fc-72ffb79136e0"
total_cost
0.0008753
cache_discount
0.0000672
upstream_inference_cost
0
provider_name
"xAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
210
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
212
wordsDialogue
212
63.6358%