NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07HTKQA6YJ2Q3WVTQQC6Z7
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.1s
Cost:
$0.003442
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
40.0831%
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 the target is a children’s party.” “Because, Bill, the grown-up parties have actual security.” “Children have security. They call it ‘aunties.’” “Noted. Still easier.” “You say ‘easier’ like you’re discussing tea.” “I am discussing tea. We’re having tea after.” “We are not having tea after we steal birthday gifts from a room full of small humans.” “Technically, they’re presents.” “Technically, that makes it worse.” “Bill, focus. The presents will be piled by the cake.” “Why do you know that?” “Because every party has the same tragic geography.” “Tragic geography?” “Yes. Cake in the middle. Presents in a corner. Adults pretending not to panic.” “And you think we can just waltz in?” “Bill, we are thieves. Waving is our whole brand.” “Our brand is not being recognized by toddlers.” “Exactly. Low profile.” “I hate that this sounds sensible.” “It is sensible.” “It is awful.” “It is profitable.” “It is sticky.” “It is brief.” “It is morally disgusting.” “It is a children’s party, Bill, not a cathedral.” “Don’t make it sound smaller.” “Fine. You carry the sack.” “I’m not carrying the sack.” “You’re always saying that.” “Because the sack always has glitter in it.” “Then wear gloves.” “Gloves with glitter are just accusations.” “Molly?” “Yes?” “Are we the bad guys?” “Only until snack time.”
created_at
"2026-03-18T10:23:37.606Z"
3/18/2026, 10:23:37 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6390
moderation_latency
(null)
generation_time
6640
tokens_prompt
77
tokens_completion
721
native_tokens_prompt
66
native_tokens_completion
754
native_tokens_completion_images
0
native_tokens_reasoning
431
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
0.0034425
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0e2b92950b352ade0169ba7d29b4708197ac06b06322d12b28"
is_byok
false
latency
211
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-1773829417-vcTg4YWhesjgmlzN46TP"
upstream_id
"resp_0e2b92950b352ade0169ba7d29b4708197ac06b06322d12b28"
total_cost
0.0034425
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
217
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
218
wordsDialogue
218
40.0831%