NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08S6GEJ7X5EYWQEC40N7J4
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5.9s
Cost:
$0.005625
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
63.50%
Dialogue to Total Word Ratio
(details)
81.7505%
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
Bill crouched beside the hedge, watching the balloons bob above the garden fence. “Children’s parties,” Molly whispered, “are perfect. Everyone assumes the clown is the biggest threat.” Bill adjusted his tie, which was stolen, optimistically, from a laundrette mannequin. “What’s the route?” “Front gate, inflatable castle, gift table, out through the kitchen like we belong there.” “And if anyone asks?” “You’re Uncle Barry.” “I don’t look like a Barry.” “That’s why it works.” A shriek of laughter rose from the house, followed by the tinny honk of a party trumpet. Molly grinned. “Listen to that. Chaos. Cake. Custard. No security team can survive that trio.” Bill pulled on white gloves. “I still say the presents are small.” “Small?” Molly said. “Bill, those are not presents. Those are treasure chests with ribbons.” He peered over the fence. “I can see a robot, three books, and something wrapped like a football.” “Exactly,” she said. “Tonight, every child learns a lesson.” “About generosity?” “About perimeter weaknesses.” They climbed the fence, landed in a marigold bed, and marched toward the party as if invited by destiny and bad manners. “If this goes wrong,” Bill murmured, “I’m blaming the clown’s aura and your leadership style entirely.”
created_at
"2026-03-18T10:45:07.738Z"
3/18/2026, 10:45:07 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4971
moderation_latency
(null)
generation_time
5420
tokens_prompt
77
tokens_completion
348
native_tokens_prompt
66
native_tokens_completion
1239
native_tokens_completion_images
0
native_tokens_reasoning
943
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
0.005625
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0e66278293b211b90169ba8233cb18819099f16d5f02630929"
is_byok
false
latency
168
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-1773830707-XKgKdmOXSFEOEdwQo0a5"
upstream_id
"resp_0e66278293b211b90169ba8233cb18819099f16d5f02630929"
total_cost
0.005625
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
201
63.50%
Dialogue to Total Word Ratio
Ratio: 58.21%, Deviation: 8.21%
neededClean
false
wordsTotal
201
wordsDialogue
117
81.7505%