NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-12-01KKHZMBA14QN6NZ4C1TQ8DEBA
Run Details
Model:
Grok 4.20 (Beta, Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
31.9s
Cost:
$0.053142
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
99.90%
Dialogue to Total Word Ratio
(details)
99.9442%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Deep in the shadows of their beat-up old van parked across the street from the loud and chaotic children's party filled with bright balloons and loud laughter, Molly and Bill were carefully finalizing their most ridiculous plan yet for the ultimate heist of all time. Molly adjusted her colorful wig with determination while a very nervous Bill looked increasingly worried about the whole crazy idea they had come up with. "This is our big score," said Molly confidently. "We'll crash the party disguised as extra clowns." Bill frowned deeply with concern. "But what about the kids? They scare me more than cops." "Relax. We wait for the piƱata to break, then swoop in on the presents," Molly assured him calmly. "You distract with bad jokes and I'll bag the goods." "Okay, but I want the video game and the toy robot," Bill negotiated eagerly. "And how do we escape without them noticing us at all?" "Simple. Through the back fence into the alley. No one will suspect thieves at a birthday bash," she explained with a laugh. Bill sighed deeply in resignation. "This better work. Last heist was a disaster with those angry ducks chasing us for miles."
created_at
"2026-03-12T21:35:49.574Z"
3/12/2026, 9:35:49 PM
model
"x-ai/grok-4.20-beta-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
31104
moderation_latency
(null)
generation_time
31827
tokens_prompt
77
tokens_completion
289
native_tokens_prompt
184
native_tokens_completion
8834
native_tokens_completion_images
0
native_tokens_reasoning
8594
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
0.0531416
router
(null)
provider_responses
0
endpoint_id
"33f49f24-a0de-4dcf-872d-ca514e83fbae"
id
"91d56c89-7df6-b127-4b8a-c4dfd13e1edf"
is_byok
false
latency
342
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-1773351349-tKh4Tay4OAi2v8pqrVJh"
upstream_id
"91d56c89-7df6-b127-4b8a-c4dfd13e1edf"
total_cost
0.0531416
cache_discount
0.0002304
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
198
99.90%
Dialogue to Total Word Ratio
Ratio: 51.76%, Deviation: 1.76%
neededClean
false
wordsTotal
199
wordsDialogue
103
99.9442%