NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-12-01KKHYSHNZXTS39N0S5RVF6S6B
Run Details
Model:
Grok 4.20 (Beta, Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
29.2s
Cost:
$0.031753
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
99.78%
Dialogue to Total Word Ratio
(details)
99.7641%
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, listen up. We break into that children's party right when they blow out the candles. That's our window of opportunity," Molly said. "Window? Molly, this is a kiddie bash not Fort Knox. What are we gonna do, steal the pin the tail on the donkey game?" Bill said. "No, the presents, all of them. Those boxes are loaded with the latest gadgets and toys that we can fence for good money. It's brilliant because no one expects thieves at a birthday party," Molly said. "True, but how do we blend in? I don't want to wear a silly costume," Bill said. "We go as clowns, obviously. You'll distract the kids with balloon animals while I bag up the gifts under the table. Then we make our getaway in the ice cream truck we stole last week," Molly said. "But the parents? And what if the birthday kid cries?" Bill said. "Parents will be busy with cake, and one fake present swap will do the trick. We'll leave them a bag of rocks wrapped nice. They'll be none the wiser," Molly said. "Okay, you're the boss. But if we get caught it's your fault. Stealing from kids feels low even for us," Bill said.
created_at
"2026-03-12T21:21:11.364Z"
3/12/2026, 9:21:11 PM
model
"x-ai/grok-4.20-beta-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
28340
moderation_latency
(null)
generation_time
29066
tokens_prompt
77
tokens_completion
274
native_tokens_prompt
184
native_tokens_completion
5250
native_tokens_completion_images
0
native_tokens_reasoning
4996
native_tokens_cached
64
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
0.0317528
router
(null)
provider_responses
0
endpoint_id
"33f49f24-a0de-4dcf-872d-ca514e83fbae"
id
"ac9fb189-ec18-5fcf-5d24-3830774d922b"
is_byok
false
latency
235
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-1773350471-z5a0ywUWoyDWMT7oJAYS"
upstream_id
"ac9fb189-ec18-5fcf-5d24-3830774d922b"
total_cost
0.0317528
cache_discount
0.0001152
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
99.78%
Dialogue to Total Word Ratio
Ratio: 92.16%, Deviation: 2.16%
neededClean
false
wordsTotal
204
wordsDialogue
188
99.7641%