NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1H0A8XF0DA7JTXNJRC3JPB
Run Details
Model:
GPT-5.4
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.7s
Cost:
$0.004560
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
60.0948%
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 community hall’s recycling bins, dressed in black so theatrical they looked less like criminals and more like understudies for a gloomy mime troupe. Through the window came the shriek of sugar-powered children and the wobbling chorus of a magician losing control of a rabbit. Molly unfolded a crayon-sketched floor plan stolen from a seven-year-old’s backpack. Balloons bobbed in the reflected light like sentries with cheerful faces. A clown on stilts patrolled the doorway, making the operation feel unnecessarily advanced. “Grab gifts, avoid cake,” Molly whispered. Bill adjusted his tiny grappling hook, which was actually a bent fondue fork tied to string. “And if the clown sees us?” “Then act natural,” she said. “No one questions a panicked adult at a children’s party.” Inside, a mountain of presents sat beneath a banner reading HAPPY BIRTHDAY ARCHIE!!! in letters large enough to be seen from orbit. Bill’s eyes gleamed with professional admiration. There were dinosaurs, glittery boxes, suspiciously expensive electronics hidden in gift bags decorated with pirates. A hired princess swept past the window, singing to a child who was weeping into a juice carton. Bill crossed himself with a glow stick. Molly checked her watch, waiting for the sacred moment every thief respected: the instant before pass-the-parcel turned feral and all adult supervision collapsed entirely.
created_at
"2026-03-06T12:12:22.182Z"
3/6/2026, 12:12:22 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
432
moderation_latency
(null)
generation_time
10669
tokens_prompt
77
tokens_completion
375
native_tokens_prompt
66
native_tokens_completion
293
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
0.00456
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0897052773acb9470169aac4a63c148190b3212472da3319cd"
is_byok
false
latency
146
model_permaslug
"openai/gpt-5.4-20260305"
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-1772799142-prTHizxg8uvYSeJw9aOy"
upstream_id
"resp_0897052773acb9470169aac4a63c148190b3212472da3319cd"
total_cost
0.00456
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
20.19%
Matches word count
n/a
neededClean
false
words
220
100.00%
Dialogue to Total Word Ratio
Ratio: 10.18%, Deviation: 0.18%
neededClean
false
wordsTotal
226
wordsDialogue
23
60.0948%