NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0AJSWJ5B1G63CD3MJ9GJ9S
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
46.8s
Cost:
$0.033192
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
99.9950%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
The moon hung over Birchwood Hall, where balloons bobbed like nervous jellyfish. Molly adjusted her gloves and studied the children’s party through the hedge. It looked less like a celebration and more like a weather event. Bill, crouched beside her, was chewing a biscuit. “Bill, smile and nod.” “Why?” “Because parents tip well when they think you’re family.” “And the clown scares me.” “Excellent.” Molly pointed at the gift table, where presents gleamed beneath ribbons like tiny hostage planets. She whispered that they should wait for the magician’s rabbit; when he screamed, they would blend with the parents, lift the boxes into the pram, and stroll out looking tragic. Bill peered at the pram parked by the cake. It contained only a sunhat, three soggy crackers, and a rubber duck wearing sunglasses. The band began a rendition of “Happy Birthday,” sounding like a brass argument. Children whooped, parents clapped, and the magician marched onstage. The last thing either thief noticed was the birthday child, who waved the foam sword like a tiny, delighted stern customs officer. Molly straightened her cap. Bill swallowed, remembered the duck, and nodded with professional shame. Together they slipped toward presents, like respectable relatives in silence.
created_at
"2026-03-18T11:16:35.361Z"
3/18/2026, 11:16:35 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
46435
moderation_latency
(null)
generation_time
46630
tokens_prompt
77
tokens_completion
2133
native_tokens_prompt
66
native_tokens_completion
7365
native_tokens_completion_images
0
native_tokens_reasoning
7098
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
0.033192
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_00492edc89e76ee40169ba89936e70819493c166f9e3934d78"
is_byok
false
latency
216
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-1773832595-P2BytrHqs0TawiHB8UJx"
upstream_id
"resp_00492edc89e76ee40169ba89936e70819493c166f9e3934d78"
total_cost
0.033192
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
99.99%
Dialogue to Total Word Ratio
Ratio: 11.00%, Deviation: 1.00%
neededClean
false
wordsTotal
200
wordsDialogue
22
99.9950%