NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM079VZFDCNC4Z753150JEHY
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.4s
Cost:
$0.001499
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
6.13%
Dialogue to Total Word Ratio
(details)
53.0559%
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, are you sure this is the right party?” Bill whispered, peering through the hedge at the balloons wobbling in the wind. “It’s a children’s party, Bill. The banner says ‘Happy Birthday, Leo,’ and there’s a clown by the gate. That’s as right as crime gets.” “I thought we were professionals.” “We are professionals. We just happen to be employed by chaos.” Bill adjusted his black gloves. “Remind me again why we’re stealing presents from six-year-olds?” “Because,” Molly said, “adults hide money in offices. Children get gifted tablets, train sets, and the occasional gold-plated dinosaur. Rich pickings.” “Gold-plated dinosaur?” “Don’t judge the market.” A burst of laughter came from inside the house. Bill flinched. “What if they ask for our names?” “Then you say Bill.” “That’s not a plan.” “It is if you say it confidently.” Bill glanced at the pile of wrapped presents visible through the window. “I hate that I’m tempted.” “You hate that I’m right.” “I hate that too.” Molly smiled. “Listen. We go in through the back, blend in, and leave with the haul before anyone notices.” “And if they do notice?” Molly shrugged. “We apologize, hand back the smallest box, and run like villains with excellent posture.”
created_at
"2026-03-18T10:19:16.861Z"
3/18/2026, 10:19:16 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2602
moderation_latency
(null)
generation_time
2764
tokens_prompt
77
tokens_completion
501
native_tokens_prompt
66
native_tokens_completion
322
native_tokens_completion_images
0
native_tokens_reasoning
34
native_tokens_cached
0
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
0.0014985
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_09e2b8d545b9ed370169ba7c24f3108195aa93ae66d19285df"
is_byok
false
latency
201
model_permaslug
"openai/gpt-5.4-mini-20260317"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773829156-OAofLpruxsLPhv3EJR15"
upstream_id
"resp_09e2b8d545b9ed370169ba7c24f3108195aa93ae66d19285df"
total_cost
0.0014985
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
6.13%
Dialogue to Total Word Ratio
Ratio: 77.07%, Deviation: 12.93%
neededClean
false
wordsTotal
205
wordsDialogue
158
53.0559%