NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-01-01KQHRC1Y72C7JXRMHDBJVT377
Run Details
Model:
Grok 4.20
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4.9s
Cost:
$0.000743
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
0.03%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
0.0152%
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 hedge, peering through binoculars at the bouncy castle where tiny tyrants shrieked over balloon animals. Bill adjusted his ridiculous clown wig and sighed. “We hit the party at peak present frenzy,” Molly whispered. “Right after cake, before the sugar crash.” Bill grinned. “I’ll distract with my award-winning balloon giraffe routine. You swoop in like a raccoon with a duffel bag.” “Those kids are vicious, Bill. Last week one bit a piñata handler.” “Which is why I’m wearing three layers of bite-proof padding under the polka dots. We grab the mountain of gifts, bolt through the backyard, and vanish before ‘Happy Birthday’ finishes.” Molly checked her watch. “Target arrives in twenty. Remember, no eye contact with the birthday boy. He’s got the stare of a loan shark.” “Copy that. One clown, one raccoon, zero mercy.” Bill offered a fist bump. “Let’s go ruin some childhoods.” Molly bumped it, then zipped her bag of tranquilizer-laced juice boxes. “For the greater good. Or at least our greater bank account.”
created_at
"2026-05-01T12:31:45.099Z"
5/1/2026, 12:31:45 PM
model
"x-ai/grok-4.20-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
435
moderation_latency
(null)
generation_time
4872
tokens_prompt
77
tokens_completion
292
native_tokens_prompt
182
native_tokens_completion
233
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
64
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.0007428
router
(null)
provider_responses
0
endpoint_id
"3ecee37f-b217-4093-87fb-aaf0afe307af"
id
"b9a875ee-2bc3-2c70-0e8c-81bc08149fef"
is_byok
false
latency
121
model_permaslug
"x-ai/grok-4.20-20260309"
provider_name
"xAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777638705-knDjlFkiV8VOPXrm66Pl"
session_id
(null)
api_type
"completions"
id
"gen-1777638705-2zZDwtVbfd3sqIwg1UZz"
upstream_id
"b9a875ee-2bc3-2c70-0e8c-81bc08149fef"
total_cost
0.0007428
cache_discount
0.0000672
upstream_inference_cost
0
provider_name
"xAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
0.03%
Matches word count
n/a
neededClean
false
words
170
0.00%
Dialogue to Total Word Ratio
Ratio: 69.94%, Deviation: 59.94%
neededClean
false
wordsTotal
173
wordsDialogue
121
0.0152%