NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM08VSFAT8FXR009HJ0XPSYA
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2.9s
Cost:
$0.001607
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9595%
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 crouched behind the bakery van, peering at the gaudy banner stretched across the garden gate: HAPPY BIRTHDAY, TOMMY. Balloons bobbed in the evening breeze like colored spies. Inside, children shrieked with frosting-smeared joy while the presents piled beneath the picnic table shimmered in wrapping paper and ribbon. Bill adjusted his tie, which was fake, like most of his confidence. “Are we really doing this?” he whispered. Molly grinned. “We’re professionals.” “Professionals don’t target six-year-olds.” “They do if the loot is alphabet blocks, model rockets, and a remote-control triceratops.” Bill swallowed. “That triceratops looked expensive.” A clown stumbled past them, juggling oranges and failing upward into applause. Molly held up a silver key ring. “Kitchen entrance is clear. We take the cake box as camouflage, stroll in, and swap the gifts for the empty crate.” “And if anyone asks?” “Smile like caterers. Panic later.” Bill nodded, though his knees had begun a separate plan. “I hate how elegant this is.” From inside came a chorus of singing, followed by the dramatic tearing of paper. Molly glanced at the mountain of presents and sighed. “By midnight,” she said, “that entire room belongs to us.” Bill squared his shoulders. “Then let’s rob childhood with style.”
created_at
"2026-03-18T10:46:32.694Z"
3/18/2026, 10:46:32 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2443
moderation_latency
(null)
generation_time
2641
tokens_prompt
77
tokens_completion
475
native_tokens_prompt
66
native_tokens_completion
346
native_tokens_completion_images
0
native_tokens_reasoning
55
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
0.0016065
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_00f8350c7a65f31b0169ba8288c5c48190a598b9372296c0f6"
is_byok
false
latency
223
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-1773830792-IhSmUDnlRbKTWjV6lDKr"
upstream_id
"resp_00f8350c7a65f31b0169ba8288c5c48190a598b9372296c0f6"
total_cost
0.0016065
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
0.00%
Dialogue to Total Word Ratio
Ratio: 39.61%, Deviation: 29.61%
neededClean
false
wordsTotal
207
wordsDialogue
82
49.9595%