NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-01-01KQHR6W1ACZVGS9AZ3Z7WYW5R
Run Details
Model:
Grok 4.20
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
4.2s
Cost:
$0.000898
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
90.6352%
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
“I still say we hit the clown first,” Molly whispered, peering over the hedge at the bouncing castle. “Take out the entertainment, the kids’ll be chaos. Easy pickings.” Bill adjusted his tiny party hat. “Clown’s got balloons, Mol. You pop those and we’ve got twenty screaming gremlins on us like piranhas. We go in through the bouncy castle. Silent. Ninja-like.” “Ninjas don’t wear velcro shoes that squeak, Bill.” “They do if they’re committed. Look, we grab the gift table while they’re singing Happy Birthday. I’ll be the mysterious magician. You be the face-painting lady. Classic misdirection.” Molly snorted. “Last time you did magic you pulled a sock out of a kid’s ear and got chased by an angry dad. We’re not improvising this time. Rope, duct tape, and that comically large sack you stole from Santa’s clearance bin.” “Fine. But I’m wearing the fake mustache. I look trustworthy with facial hair.” “You look like a children’s party predator with that thing. Lose the mustache. We go in clean, we go out rich. And if anyone asks, we’re from the rival balloon company. Corporate espionage, very serious.” Bill grinned. “God I love stealing from children. Feels wrong in all the right ways.” “Focus, you idiot. Cake’s at three. We move at two fifty-eight.”
created_at
"2026-05-01T12:28:55.215Z"
5/1/2026, 12:28:55 PM
model
"x-ai/grok-4.20-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
339
moderation_latency
(null)
generation_time
4147
tokens_prompt
77
tokens_completion
356
native_tokens_prompt
182
native_tokens_completion
295
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
0.0008978
router
(null)
provider_responses
0
endpoint_id
"3ecee37f-b217-4093-87fb-aaf0afe307af"
id
"b6be22db-6cbe-9543-9488-fd559dc30a03"
is_byok
false
latency
74
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-1777638535-Eq2ILramlth4TprMhzVh"
session_id
(null)
api_type
"completions"
id
"gen-1777638535-TFwbYZLvLOkPqTJ1QzLH"
upstream_id
"b6be22db-6cbe-9543-9488-fd559dc30a03"
total_cost
0.0008978
cache_discount
0.0000672
upstream_inference_cost
0
provider_name
"xAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
212
100.00%
Dialogue to Total Word Ratio
Ratio: 90.70%, Deviation: 0.70%
neededClean
false
wordsTotal
215
wordsDialogue
195
90.6352%