NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07KV6KQFGNQA87HHYG3XEX
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.1s
Cost:
$0.001350
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
1.36%
Dialogue to Total Word Ratio
(details)
43.8704%
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
“Bill, tell me again why we’re crouched behind a clown car outside a seven-year-old’s birthday party,” Molly whispered. “Because,” Bill said, adjusting his black gloves, “the mark is rich in loot, the security is laughable, and the frosting budget alone suggests valuables.” Molly peered through a hedge at the backyard. “You mean presents.” “I mean presents,” Bill said. “But I prefer the romantic term.” A burst of children’s laughter floated over the fence, followed by a shriek from a helium balloon. Molly flinched. “This feels wrong.” “Of course it does,” Bill said. “That’s how you know it’s a proper heist.” She sighed. “We are stealing from children.” “Technically,” Bill said, “we are liberating gifts from an unregulated distribution system.” Molly turned to him. “Did you rehearse that?” “I wrote it on the drive over.” A woman’s voice called from inside, “Okay, kids, present time!” Bill’s eyes shone. “Now’s our window.” Molly grabbed his sleeve. “We are not doing this if there’s a bounce castle.” Bill blinked. “There’s a bounce castle?” She stared at him. “You didn’t notice the bounce castle?” He grinned. “Molly, that’s not a complication. That’s cover.”
created_at
"2026-03-18T10:24:43.743Z"
3/18/2026, 10:24:43 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
383
moderation_latency
(null)
generation_time
1930
tokens_prompt
77
tokens_completion
360
native_tokens_prompt
66
native_tokens_completion
289
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
0.00135
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_04339b315db16e2f0169ba7d6bd3448193a6857990668023a9"
is_byok
false
latency
198
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-1773829483-SHA6zRuJAT10NAwyfmHN"
upstream_id
"resp_04339b315db16e2f0169ba7d6bd3448193a6857990668023a9"
total_cost
0.00135
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
189
1.36%
Dialogue to Total Word Ratio
Ratio: 64.40%, Deviation: 14.40%
neededClean
false
wordsTotal
191
wordsDialogue
123
43.8704%