NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08BEFGD8MEYH1DB7357XNS
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.5s
Cost:
$0.001521
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
9.61%
Matches word count
(details)
99.85%
Dialogue to Total Word Ratio
(details)
54.7310%
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 flattened herself behind the bakery van and peered at the pastel house. “You’re sure this is the one?” Bill adjusted his cap and sniffed. “The one with the inflatable giraffe, the brass band of children, and enough loot to make Santa file for bankruptcy? Yes.” “Presents are stacked by the hallway,” Molly whispered. “I saw them through the window. Ribbon mountain. Card avalanche.” Bill grinned. “Beautiful. We go in as balloon delivery.” “We don’t have balloons.” “We have confidence.” “That’s not a balloon.” “It’s cheaper.” Inside, the party shrieked with sugar-fueled joy, while parents chatted near the cake table and one clown twisted a dog into a regrettable swan. Molly and Bill slipped through the side gate with a borrowed trolley and two solemn faces. Bill said, “If anyone asks, we’re from the generosity department.” Molly whispered, “That sounds fake.” “Everything we do sounds fake.” They reached the pile of presents, glittering under a paper lantern. Molly lifted the first box. “Heavy.” “Excellent,” said Bill. “That means love.” “Or batteries.” “Even better. Batteries are hope, but practical.”
created_at
"2026-03-18T10:37:37.148Z"
3/18/2026, 10:37:37 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1437
moderation_latency
(null)
generation_time
2327
tokens_prompt
77
tokens_completion
336
native_tokens_prompt
66
native_tokens_completion
327
native_tokens_completion_images
0
native_tokens_reasoning
70
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
0.001521
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0c0d39480bd3fb580169ba807137cc8194b3458e950a6bfeee"
is_byok
false
latency
179
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-1773830257-Ltfdi4Uyf4FEcHt5ojGf"
upstream_id
"resp_0c0d39480bd3fb580169ba807137cc8194b3458e950a6bfeee"
total_cost
0.001521
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
9.61%
Matches word count
n/a
neededClean
false
words
178
99.85%
Dialogue to Total Word Ratio
Ratio: 51.96%, Deviation: 1.96%
neededClean
false
wordsTotal
179
wordsDialogue
93
54.7310%