NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0A7S187KTWDFRQDNE3HKBQ
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.2s
Cost:
$0.006543
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
50.0000%
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 crouched behind the hedges, watching the glittering house where balloons bobbed like nervous spies. “Tell me again why we’re robbing a room full of five-year-olds?” she whispered. Bill adjusted his tie, which was mostly for disguise and partly because he liked the idea of respectability. “Because children are terrible witnesses, and the cake budget means there’s cash somewhere.” “That’s a deeply depressing theory,” Molly said. “It’s also true. We enter through the garden, blend in with the entertainers, and exit with the presents before anyone notices the blue van.” Molly frowned. “You rented a blue van?” “It was the cheapest.” “The cheapest is always a trap.” “The cheapest is also available.” Bill peered at the house. “Do you have the fake clown hats?” “I have the fake clown hats, but I want the record to show I hate every syllable of this plan.” “Excellent. That means you’re focused.” A child’s laugh floated through the window, bright and innocent. Molly swallowed. “Bill, if this goes wrong, I’m blaming your face.” Bill grinned. “Fair. But if it goes right, we’re the most thoughtful thieves in town.” “And the presents?” Molly asked. “Only the unwrapped ones,” Bill said. “We’re thieves, not monsters.”
created_at
"2026-03-18T11:10:34.038Z"
3/18/2026, 11:10:34 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9632
moderation_latency
(null)
generation_time
10065
tokens_prompt
77
tokens_completion
724
native_tokens_prompt
66
native_tokens_completion
1443
native_tokens_completion_images
0
native_tokens_reasoning
1164
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
0.006543
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_07558bd9254dbb990169ba882a1de48193bf0cfe6c7c8e117d"
is_byok
false
latency
212
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-1773832234-fEmkemICdmyDVSWhgvbf"
upstream_id
"resp_07558bd9254dbb990169ba882a1de48193bf0cfe6c7c8e117d"
total_cost
0.006543
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
0.00%
Dialogue to Total Word Ratio
Ratio: 69.31%, Deviation: 19.31%
neededClean
false
wordsTotal
202
wordsDialogue
140
50.0000%