NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09XQEYAVQ385YP0N7YXRE6
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5.4s
Cost:
$0.005904
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
75.44%
Dialogue to Total Word Ratio
(details)
87.7178%
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 crouched behind the hedge, peering at the rainbow balloons bobbing over the garden fence. Bill adjusted his tie, which was already a crime against tailoring. “Tell me again why we’re doing this,” Bill whispered. “Because,” Molly said, “the Finchley children have the largest haul of birthday presents in the district, and we have been badly underemployed.” Bill frowned. “That is not a reason. That is a parish newsletter.” “Focus. We go in as entertainers.” “You can’t juggle.” “I can, if the juggling balls are emotionally supportive.” Bill looked at the party, where a magician was making a rabbit disappear into applause. “So we pose as the act after the magician?” “No. We pose as the emergency backup clowns.” “There’s no such thing.” “There is if you say it confidently.” Bill sighed. “And the presents?” “We borrow them.” “Borrow?” “Forever.” He straightened his gloves. “Molly, this is monstrous.” Molly grinned. “It’s also festive. Besides, who suspects thieves at a party with a bouncy castle?” Bill glanced at the castle. “I do.” “Excellent,” Molly said. “You’re learning.” Then they heard the birthday song begin, and both of them smiled like professionals who had just found a lock made of frosting.
created_at
"2026-03-18T11:05:04.747Z"
3/18/2026, 11:05:04 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4751
moderation_latency
(null)
generation_time
5225
tokens_prompt
77
tokens_completion
372
native_tokens_prompt
66
native_tokens_completion
1301
native_tokens_completion_images
0
native_tokens_reasoning
1019
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
0.005904
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0efcab69c67e6b1f0169ba86e0cc408196821f717a3c40f9ee"
is_byok
false
latency
176
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-1773831904-oKSWxeQv8z2fdKo0kZor"
upstream_id
"resp_0efcab69c67e6b1f0169ba86e0cc408196821f717a3c40f9ee"
total_cost
0.005904
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
199
75.44%
Dialogue to Total Word Ratio
Ratio: 57.29%, Deviation: 7.29%
neededClean
false
wordsTotal
199
wordsDialogue
114
87.7178%