NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM096W5FJ2ZJQCW64DP10SHB
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.0s
Cost:
$0.001359
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
0.01%
Dialogue to Total Word Ratio
(details)
49.9946%
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
Molly and Bill crouched behind the hedge outside Mrs. Pemberton’s garden, watching balloons bob like smug little spies over the fence. Inside, a tinny playlist of pirate songs drifted through the warm air, along with the shrieks of delighted children and the occasional crackle of a paper crown being crushed underfoot. Bill adjusted his black gloves. “We really doing this?” Molly peered through the slats in the gate. “We’re retrieving assets.” “Assets wrapped in penguins and dinosaurs,” Bill said. “That’s still stealing presents from children.” “Children,” Molly whispered, “are famously terrible at security.” As if on cue, a small boy in a captain’s hat raced past the window clutching a juice box, leaving the side gate propped open with a plastic shovel. Molly smiled with professional admiration. “See? Amateur hour.” Bill winced. “You brought the sack?” “I brought two sacks.” “Why?” “In case they’ve got books.” They slipped through the gate, past a tower of cupcakes, and into the chaos of streamers and sugar. The presents waited beneath a banner that read HAPPY BIRTHDAY, NINA, sparkling like a treasure hoard. Bill swallowed. “Last chance,” he murmured. Molly cracked her knuckles. “For what?” “To become very bad people in front of a clown.”
created_at
"2026-03-18T10:52:35.9Z"
3/18/2026, 10:52:35 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
430
moderation_latency
(null)
generation_time
1711
tokens_prompt
77
tokens_completion
362
native_tokens_prompt
66
native_tokens_completion
291
native_tokens_completion_images
0
native_tokens_reasoning
0
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
0.001359
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_083c50e25add82030169ba83f3fa2481978b75641ce7d8da9f"
is_byok
false
latency
218
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-1773831155-CjDvtgi3fTVTRmXxhmMt"
upstream_id
"resp_083c50e25add82030169ba83f3fa2481978b75641ce7d8da9f"
total_cost
0.001359
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
0.01%
Dialogue to Total Word Ratio
Ratio: 27.72%, Deviation: 17.72%
neededClean
false
wordsTotal
202
wordsDialogue
56
49.9946%