NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-12-01KKHZGZGH0G8MHPF7C0YXGQ6Y
Run Details
Model:
Grok 4.20 (Beta)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.0s
Cost:
$0.001844
Provider:
xAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
99.9955%
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
Molly peered over the hedge at the bouncing castle. “Bill, you absolute walnut, we’re not nicking the cake. The presents. All of them. In and out before the little monsters finish ‘Happy Birthday.’” Bill adjusted his comically small party hat. “Molly, love, I still say we should’ve gone with the clown disguise. Nobody suspects a man in an orange wig holding a seltzer bottle.” “We’re not clowns, we’re professionals. You’re the ‘fun uncle’ with the van. I’m the glamorous aunt who spikes the punch with laxative. Timing is everything.” “Relaxative punch? That’s evil.” “Efficient. Ten minutes later it’s just us and a mountain of wrapped joy. Now, the piñata is the decoy. While they’re beating the living daylights out of it, we load the booty.” Bill scratched his chin. “What if someone wants their present back?” “Then you do the thing with the tears. You’re very good at fake crying.” “I prefer the fake fainting. More theatrical.” “Fine. Fake faint, I’ll scream ‘He’s having a turn!’ and we scarper with the haul. Any questions?” “Yeah. Do we keep the giant teddy or flog it on eBay?” Molly grinned. “We keep the teddy. He’s called Mr. Snuggles now. He’s our getaway driver.”
created_at
"2026-03-12T21:33:59.19Z"
3/12/2026, 9:33:59 PM
model
"x-ai/grok-4.20-beta-20260309"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
745
moderation_latency
(null)
generation_time
1786
tokens_prompt
77
tokens_completion
346
native_tokens_prompt
182
native_tokens_completion
285
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
0.0018436
router
(null)
provider_responses
0
endpoint_id
"33f49f24-a0de-4dcf-872d-ca514e83fbae"
id
"863eed8d-c442-ced1-3ea6-cebfef904465"
is_byok
false
latency
708
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-1773351239-ye9L0nSyoa3tboW51aXM"
upstream_id
"863eed8d-c442-ced1-3ea6-cebfef904465"
total_cost
0.0018436
cache_discount
0.0002304
upstream_inference_cost
0
provider_name
"xAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
201
99.99%
Dialogue to Total Word Ratio
Ratio: 89.05%, Deviation: 0.95%
neededClean
false
wordsTotal
201
wordsDialogue
179
99.9955%