NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07BN73MXMK4JC98WG3PMDK
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
3.2s
Cost:
$0.001715
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
89.07%
Dialogue to Total Word Ratio
(details)
70.4959%
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, you’ve got the map?” “Of course I’ve got the map, Bill. Do I look like someone who’d rob a party blind without a map?” “You look like someone who’d rob a party blind with a spoon.” “Shut it. The children’s party is in the garden marquee. Presents stacked by the cake table. Easy.” “Easy? There are balloons.” “Yes, and?” “Balloons have eyes, Molly. They watch.” “You’re thinking of clowns.” “That’s worse.” “Listen carefully. We go in as entertainers.” “I’m not wearing a tiny hat.” “You’re wearing the hat. I’m the magician.” “You can’t do magic.” “I can do one trick.” “Name it.” “I make presents disappear.” “They’re wrapped.” “Exactly.” Bill squinted. “What if the birthday child asks questions?” “We say it’s a recycling lesson.” “Brilliant. What if the parents stop us?” Molly grinned. “I brought cupcakes.” “You brought bribery.” “I brought frosting.” “That’s somehow more criminal.” “Focus, Bill. We enter, we compliment the cake, we distract the adults, and then we load the presents into the clown car.” “We have a clown car?” “No.” “Then why did you say it?” “Because you looked worried.” “I am worried.” “Good. Worried thieves are careful thieves.” “And what are happy thieves?” “Dead,” said Molly, straightening her gloves. “Now smile. We’re going to make a child’s birthday very memorable.”
created_at
"2026-03-18T10:20:15.471Z"
3/18/2026, 10:20:15 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2667
moderation_latency
(null)
generation_time
2928
tokens_prompt
77
tokens_completion
566
native_tokens_prompt
66
native_tokens_completion
370
native_tokens_completion_images
0
native_tokens_reasoning
45
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
0.0017145
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0ce83660a02197c50169ba7c5f88f08197a51e18964f0dc5a5"
is_byok
false
latency
205
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-1773829215-ACxcalYsvqNMel5eWSH3"
upstream_id
"resp_0ce83660a02197c50169ba7c5f88f08197a51e18964f0dc5a5"
total_cost
0.0017145
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
51.93%
Matches word count
n/a
neededClean
false
words
216
89.07%
Dialogue to Total Word Ratio
Ratio: 95.83%, Deviation: 5.83%
neededClean
false
wordsTotal
216
wordsDialogue
207
70.4959%