NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-01-01KQHQGMA13QS16JXKF775NN7M
Run Details
Model:
Grok 4.20
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.7s
Cost:
$0.000753
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.8722%
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 at the balloon-festooned house where sugar-high screams pierced the afternoon. Bill adjusted his comically small party hat and checked his watch. “This is insane,” Molly whispered. “We’re hitting a kiddie party for presents?” Bill grinned, teeth flashing. “Kids get the good stuff these days. You seen those drone kits? That’s fenceable.” Molly rolled her eyes. “We’re not stealing from six-year-olds, Bill. That’s a new low even for us.” “Relax. We go in as the hired clowns. I already stole the costumes. You do the face paint, I’ll work the crowd. When they do the big present reveal, we swap the tablecloth for our own and wheel the whole pile out like it’s part of the magic act.” Molly stared at him. “You want us to clown our way through armed with a tablecloth and face paint?” “Exactly. Classic misdirection. Nobody suspects the guy in the giant red nose.” A burst of laughter erupted from inside as another game began. Molly sighed, already picturing the headlines: “Clown Couple Cleans Out Birthday Bash.” “Fine,” she muttered. “But if we get recognized by some PTA mom, I’m throwing you under the bouncy castle.”
created_at
"2026-05-01T12:16:46.406Z"
5/1/2026, 12:16:46 PM
model
"x-ai/grok-4.20-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
393
moderation_latency
(null)
generation_time
5394
tokens_prompt
77
tokens_completion
326
native_tokens_prompt
182
native_tokens_completion
264
native_tokens_completion_images
(null)
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)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.0007531
router
(null)
provider_responses
0
endpoint_id
"3ecee37f-b217-4093-87fb-aaf0afe307af"
id
"a5ec0f53-9894-869f-58c3-a8756aa5cf2f"
is_byok
false
latency
93
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-1777637806-CXsf6qv1Kz3ulkkmRBXI"
session_id
(null)
api_type
"completions"
id
"gen-1777637806-su2400cejFGtesHbenwO"
upstream_id
"a5ec0f53-9894-869f-58c3-a8756aa5cf2f"
total_cost
0.0007531
cache_discount
0.0001344
upstream_inference_cost
0
provider_name
"xAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
196
0.00%
Dialogue to Total Word Ratio
Ratio: 69.00%, Deviation: 59.00%
neededClean
false
wordsTotal
200
wordsDialogue
138
49.8722%