NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-06-01KK1GBHGJ4PB1C2ZVJZBSEHJ1
Run Details
Model:
GPT-5.4
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.3s
Cost:
$0.004875
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
0.02%
Dialogue to Total Word Ratio
(details)
40.6453%
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 peered through the bakery window at the church hall, where balloons bobbed like nervous witnesses and a clown unloaded wrapped boxes onto a trestle table. “Bill, tell me that’s not the easiest score in London.” “It’s a children’s party,” Bill whispered. “I feel morally complicated and professionally excited.” “Focus. Presents in, presents out, no one cries except possibly the clown.” “I hate clowns. They’re like burglars who gave up and joined theatre.” Molly unfolded a crayon-scribbled map. “Entrance at the bouncy castle. Diversion near the punch bowl. Extraction through the side gate beside the inflatable pirate.” “Did you just say extraction?” “Yes. Makes theft sound healthy.” Bill adjusted his tiny paper party hat. “And my disguise?” “You’re a divorced magician.” “That’s painfully specific.” “It explains the sadness.” Inside, children shrieked as a woman in a tiara lit candles on a dinosaur cake. Bill swallowed. “What if they spot us?” “They’re six. If you produce a coin from someone’s ear, they’ll appoint you mayor.” “And you?” “Nervous aunt. Strong opinions on napkins.” Bill nodded toward the gift table. “There must be thirty presents.” “Thirty hostages,” Molly corrected. “Now smile.” Bill inhaled. “Right. We go in, charm the room, liberate the loot, and vanish before ‘Happy Birthday.’” Molly grinned. “Exactly. Crime, but festive.”
created_at
"2026-03-06T12:01:01.465Z"
3/6/2026, 12:01:01 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
388
moderation_latency
(null)
generation_time
8200
tokens_prompt
77
tokens_completion
415
native_tokens_prompt
66
native_tokens_completion
314
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
0.004875
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0edc628b361ad4890169aac1fd87e881968bf9541a764590c9"
is_byok
false
latency
165
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-1772798461-8XoikzdOm4SimG8e48Dk"
upstream_id
"resp_0edc628b361ad4890169aac1fd87e881968bf9541a764590c9"
total_cost
0.004875
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
212
0.02%
Dialogue to Total Word Ratio
Ratio: 67.14%, Deviation: 17.14%
neededClean
false
wordsTotal
213
wordsDialogue
143
40.6453%