NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0A0R7ZKMH4ZDYZS3DKSASR
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.1s
Cost:
$0.001449
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
93.1902%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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, tell me again why we’re crouched behind a hedge outside a clown-covered bungalow at four in the afternoon?" Bill whispered. "Because, Bill, the target is simple: birthday loot," Molly said. "That’s not a word criminals use." "It is when criminals are classy." "Classy burglars don’t say 'birthday loot.'" "They do if they’re stealing a mountain of presents from a party full of sugar-drunk five-year-olds." "Even saying that makes me feel sticky." "Focus. The parents will be distracted by cake, balloons, and one catastrophic magician." "What if the magician is good?" "Then we steal faster." "How do we get in?" "We’re the balloon delivery people." "We do not have balloons." "We have confidence." "That’s not the same thing." "No, but it’s more portable." Bill peered over the hedge. "There are three children guarding the presents." "Are they armed?" "One has a plastic sword." "Terrifying." "And a girl in a princess dress is reading labels." "She sounds like security." "Should we feel guilty?" "Bill, we are thieves." "Yes, but those presents have names on them." "Exactly. Efficient sorting." "You’re awful." "I’m practical. Now breathe normally and pretend we belong." A tiny voice from the gate yelled, "Are you the surprise?" Molly froze. Bill sighed. "I hate kids." Molly smiled. "Perfect. We’re in."
created_at
"2026-03-18T11:06:43.85Z"
3/18/2026, 11:06:43 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
396
moderation_latency
(null)
generation_time
2002
tokens_prompt
77
tokens_completion
390
native_tokens_prompt
66
native_tokens_completion
311
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
0.001449
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0a06c86ff24b47760169ba8743ee748190b5477777df0988af"
is_byok
false
latency
228
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-1773832003-uzViajwiWcYTNfrCgb0n"
upstream_id
"resp_0a06c86ff24b47760169ba8743ee748190b5477777df0988af"
total_cost
0.001449
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
211
100.00%
Dialogue to Total Word Ratio
Ratio: 89.77%, Deviation: 0.23%
neededClean
false
wordsTotal
215
wordsDialogue
193
93.1902%