NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08W6SEJVZ4X764K4R6W4EF
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.4s
Cost:
$0.008766
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.95%
Dialogue to Total Word Ratio
(details)
99.9757%
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 the glittering envelope in her palm and peered at the townhouse. Balloons bobbed in the window like nervous spies, and the sound of children chanting “Pin the Tail” drifted through the brick. Bill adjusted his striped scarf and tried to look sinister, which on him mostly suggested a librarian with a tax issue. “Remind me,” Molly whispered, “why are we robbing a seven-year-old’s birthday?” Bill grinned. “Because he’s got better loot than the museum.” “You mean presents.” “Presents are loot with ribbons.” Molly watched a parent carry in another tower of wrapped boxes. “That one’s larger than my first apartment.” “Exactly. We go in, mingle, become invisible, and leave with the haul.” “‘Mingle’?” she said. “You want to socialize while committing a felony?” Bill shrugged. “It’s a children’s party. Everyone expects awkward adults.” “Bill, the last time you improvised, we escaped a petting zoo with a flamingo and a juice box.” “That was strategy.” A burst of laughter rolled from inside. Molly sighed, tugged on her gloves, and smiled despite herself. “Fine,” she said. “But if anyone asks, we’re face painters.” Bill nodded solemnly. “Professional face painters.” Outside, the cake candles flickered like tiny, unhelpful witnesses already counting.
created_at
"2026-03-18T10:46:46.329Z"
3/18/2026, 10:46:46 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
8067
moderation_latency
(null)
generation_time
8251
tokens_prompt
77
tokens_completion
650
native_tokens_prompt
66
native_tokens_completion
1937
native_tokens_completion_images
0
native_tokens_reasoning
1644
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
0.008766
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_02c0d81aa59c9f780169ba829663ec8193a0e3d58e2d8549f0"
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-1773830806-1tkH1Ciu3MgBusQ9IKAD"
upstream_id
"resp_02c0d81aa59c9f780169ba829663ec8193a0e3d58e2d8549f0"
total_cost
0.008766
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
99.95%
Dialogue to Total Word Ratio
Ratio: 48.51%, Deviation: 1.49%
neededClean
false
wordsTotal
202
wordsDialogue
98
99.9757%