NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-12-01KKHZ49BR302PN061Y5TSRTZD
Run Details
Model:
Grok 4.20 (Beta)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.5s
Cost:
$0.001826
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
43.1902%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
Molly crouched behind the hedgerow, peering through a gap at the bouncing castle and sugar-crazed toddlers. Bill slid in beside her, clutching a clown mask like it might bite him. “This is the worst idea you’ve ever had,” he whispered. Molly grinned. “You said that about the museum heist. And the armored car. And your marriage. Relax. We wait till they cut the cake, then we slip in as disgruntled parents.” Bill stared at her. “We’re stealing presents from children. At a birthday party. I feel like I’m one balloon animal away from turning myself in.” “Think of it as redistribution of wealth,” she said, checking her watch. “Those kids get new toys every week. We get one solid score and we’re out of this town before the piñata’s even cold.” He groaned. “If we get caught I’m telling them you made me do it.” “Fine,” Molly said, adjusting her fake mom-bun. “But if we pull this off, I’m buying you a spine for Christmas. Now shut up and practice your ‘Where’s my little Timmy?’ face.” Bill sighed, pulled the clown mask over his head, and immediately looked ten percent more criminal. “I hate you.” “Love you too, partner. Cake’s in five. Try not to cry when the toddlers tackle you.”
created_at
"2026-03-12T21:27:03.292Z"
3/12/2026, 9:27:03 PM
model
"x-ai/grok-4.20-beta-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
332
moderation_latency
(null)
generation_time
2443
tokens_prompt
77
tokens_completion
336
native_tokens_prompt
182
native_tokens_completion
282
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
0.0018256
router
(null)
provider_responses
0
endpoint_id
"33f49f24-a0de-4dcf-872d-ca514e83fbae"
id
"4f735d98-bf5f-cc32-4d9a-6d54c739a9ce"
is_byok
false
latency
285
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-1773350823-osZunpBYt4YmVBBY9K33"
upstream_id
"4f735d98-bf5f-cc32-4d9a-6d54c739a9ce"
total_cost
0.0018256
cache_discount
0.0002304
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
211
0.00%
Dialogue to Total Word Ratio
Ratio: 67.61%, Deviation: 57.61%
neededClean
false
wordsTotal
213
wordsDialogue
144
43.1902%