NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-12-01KKHYXRG7P2E0A8DB6PZSK4WM
Run Details
Model:
Grok 4.20 (Beta, Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
39.8s
Cost:
$0.044940
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
97.69%
Dialogue to Total Word Ratio
(details)
98.8060%
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, we need to talk about this children's party heist. How exactly are we going to steal all those presents without getting caught by a horde of sugar high kids?" said Molly. "We'll go in as professional party entertainers, Molly. I'll be the clown with the giant shoes and you can be the face painter. While I'm making balloon giraffes the kids will be lined up and the presents will be ripe for the picking. We grab them during musical chairs," said Bill. "That could work but what if someone recognizes us from our last job at the circus? And are we really stooping to stealing from children?" said Molly. "Come on it's not stealing it's redistributing the wealth of toys. Those kids have too many and we have none. Plus we'll leave a note saying from Santa early. The escape is easy we'll use the trampoline in the backyard to bounce right over the fence to our waiting van," said Bill. "You're insane but I love it. Let's do it. Just promise me no one gets hit with a party favor," said Molly. "I promise Molly. This will be the funniest heist in history," said Bill.
created_at
"2026-03-12T21:23:29.421Z"
3/12/2026, 9:23:29 PM
model
"x-ai/grok-4.20-beta-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
38959
moderation_latency
(null)
generation_time
39644
tokens_prompt
77
tokens_completion
269
native_tokens_prompt
184
native_tokens_completion
7467
native_tokens_completion_images
0
native_tokens_reasoning
7231
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
0.0449396
router
(null)
provider_responses
0
endpoint_id
"33f49f24-a0de-4dcf-872d-ca514e83fbae"
id
"a27714f2-bc09-0ece-e721-96512d20b3ca"
is_byok
false
latency
293
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-1773350609-hFYGLTf90e3FLuFRBT7L"
upstream_id
"a27714f2-bc09-0ece-e721-96512d20b3ca"
total_cost
0.0449396
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
197
97.69%
Dialogue to Total Word Ratio
Ratio: 93.91%, Deviation: 3.91%
neededClean
false
wordsTotal
197
wordsDialogue
185
98.8060%