NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0AGJ4F133ESH0JGXC1NFHB
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
11.2s
Cost:
$0.008113
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.31%
Dialogue to Total Word Ratio
(details)
50.1557%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 at the glittering flyer taped to the lamppost. “A children’s party,” she said. “Look at that font. It screams frosting and panic.” Bill adjusted his hat, which was far too respectable for a thief. “And presents,” he said. “Loads of presents. Tiny heroes, giant boxes.” “Do you think we can get in?” Molly asked. Bill smiled. “I brought my best disguise.” She stared. “That is a paper crown from a cracker.” “It’s regal,” he said. “Besides, nobody suspects a man celebrating badly.” Molly folded the flyer. “We slip in, mingle, smile at the balloon animals, and when everyone’s distracted by cake—” “By cake?” Bill said. “You say that like it’s a distraction. Cake is the main villain.” “Focus,” Molly hissed. “We take the presents and vanish.” Bill nodded toward the house, where music thumped and a small voice yelled, “Who wants glitter?” “Honestly,” he said, “this feels morally confusing.” Molly grinned. “Only because it’s so festive.” He sighed. “Fine. But if we’re caught, I’m blaming the clown.” Molly snorted. “Deal. If the clown has a mustache, we call it art.” Bill patted his pocket. “And if the cake is guarded?” “Then,” she said, “we improvise with dignity tonight.”
created_at
"2026-03-18T11:15:21.881Z"
3/18/2026, 11:15:21 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
10516
moderation_latency
(null)
generation_time
10999
tokens_prompt
77
tokens_completion
597
native_tokens_prompt
66
native_tokens_completion
1792
native_tokens_completion_images
0
native_tokens_reasoning
1488
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
0.0081135
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_02f8b0d379d579c10169ba8949eeb48194833174f81c213d3e"
is_byok
false
latency
183
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-1773832521-LSdo4ZwHkQeiOEEXY52d"
upstream_id
"resp_02f8b0d379d579c10169ba8949eeb48194833174f81c213d3e"
total_cost
0.0081135
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
0.31%
Dialogue to Total Word Ratio
Ratio: 65.50%, Deviation: 15.50%
neededClean
false
wordsTotal
200
wordsDialogue
131
50.1557%