NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-12-01KKHZHXXA7D3V6W3C2TVCK1FH
Run Details
Model:
Grok 4.20 (Beta)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1.9s
Cost:
$0.001748
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3535%
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
"I can't believe we're doing this, Bill. A kids' birthday party? We're stealing from toddlers now?" "Relax, Molly. It's not the toddlers, it's the mountain of shiny presents under that bouncy castle. Easy in, easy out." "Easy? There's a clown, Bill. A clown with a grudge, probably. And that mother hen with the party hats is eyeing everyone like a hawk." "We'll go in as the magicians. You do that thing with the disappearing coin, I'll handle the smoke bombs. While they're all oohing and aahing, we shove the loot in the fake rabbit cage." "Fake rabbit cage? You said we were using the cake trolley!" "Changed my mind. Rabbits are more inconspicuous. Who suspects a fluffy bunny of grand larceny?" "You're an idiot. What about the piñata? It's shaped like a unicorn. Kids will riot if we touch it." "We leave the unicorn. But that giant teddy bear gift? Mine. I mean, ours. Think of the black market value on unopened Lego sets these days." "Bill, if we get caught, I'm saying you kidnapped me." "Fine, but if we pull this off, we're retiring on Barbie Dreamhouses and Pokémon cards. Now stop worrying and practice your evil clown laugh—we're going in."
created_at
"2026-03-12T21:34:30.319Z"
3/12/2026, 9:34:30 PM
model
"x-ai/grok-4.20-beta-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
327
moderation_latency
(null)
generation_time
1782
tokens_prompt
77
tokens_completion
307
native_tokens_prompt
182
native_tokens_completion
269
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
0.0017476
router
(null)
provider_responses
0
endpoint_id
"33f49f24-a0de-4dcf-872d-ca514e83fbae"
id
"746bd162-2908-62d3-b6bd-ae980ef12d67"
is_byok
false
latency
290
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-1773351270-6zO0AcxHv0Jnwj2ZEHam"
upstream_id
"746bd162-2908-62d3-b6bd-ae980ef12d67"
total_cost
0.0017476
cache_discount
0.0002304
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
203
wordsDialogue
203
68.3535%