NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0A28QZDYYKMYR1E16T633N
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2.3s
Cost:
$0.001643
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
2.00%
Dialogue to Total Word Ratio
(details)
35.0506%
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 peered through the rain-streaked van window and whispered, “There it is, Bill. A children’s party, full of balloons, cake, and unattended joy.” Bill adjusted his crooked tie. “You say that like joy isn’t difficult to carry.” “It’s light,” Molly said. “The presents, on the other hand, are suspiciously boxy.” Bill nodded. “I hate boxy. Boxy implies responsibility.” “Try not to become philosophical,” Molly said. “We go in, blend in, smile at the adults, and leave with every wrapped gift before anyone notices.” Bill frowned. “What if they ask who we are?” “Bill, we’re caterers.” “We’re wearing ski masks.” “Experimental caterers.” He glanced at the house. “That bouncy castle is going to judge me.” “Let it judge from a distance,” Molly said. “Remember: no panic, no running, and absolutely no opening anything labeled ‘fragile.’” Bill lifted a duffel bag. “And if the children cry?” Molly grinned. “Then we’ll know we’ve been thorough.” “That’s monstrous.” “That’s organized.” She opened the door. “Ready?” Bill sighed. “No. But my childhood was never this festive, so let’s commit a little crime.” “Good,” said Molly. “Try to look like you belong.”
created_at
"2026-03-18T11:07:33.516Z"
3/18/2026, 11:07:33 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1493
moderation_latency
(null)
generation_time
2144
tokens_prompt
77
tokens_completion
360
native_tokens_prompt
66
native_tokens_completion
354
native_tokens_completion_images
0
native_tokens_reasoning
63
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
0.0016425
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_06248f8aa14c07260169ba8775914c81978f953061498c8c99"
is_byok
false
latency
189
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-1773832053-qRqfXDzPDDa1f5IL2dRo"
upstream_id
"resp_06248f8aa14c07260169ba8775914c81978f953061498c8c99"
total_cost
0.0016425
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
68.10%
Matches word count
n/a
neededClean
false
words
186
2.00%
Dialogue to Total Word Ratio
Ratio: 75.94%, Deviation: 14.06%
neededClean
false
wordsTotal
187
wordsDialogue
142
35.0506%