NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0AND5WPHN0RYN5A8PF73VN
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.1s
Cost:
$0.001710
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
28.41%
Dialogue to Total Word Ratio
(details)
64.2069%
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 peered through the bakery window at the rainbow balloons bobbing over the community hall. “That,” she whispered, “is a fortress of cake, chaos, and unattended presents.” Bill adjusted his tie, which was already crooked. “I admire your eye for valuables, but I must protest the phrase unattended. Children are notoriously sticky.” “Perfect,” Molly said. “We’ll blend in.” Bill blinked. “We’re thirty-six.” “Spiritually, we’re eight.” A trumpet squealed from inside, followed by a burst of shrieking laughter. Molly grinned. “At the height of the party, everyone will be distracted by the magician.” “Will there be a magician?” “There will now.” Bill frowned. “And how, exactly, do we remove the gifts?” “Simple. You enter carrying the ‘cake delivery’ box.” “We have a cake delivery box?” “We do now.” He sighed, then smiled despite himself. “You’re impossible.” “And you’re bringing the wagon.” “The wagon that says Party Supplies?” “The same.” Bill looked toward the hall, where a papier-mâché dinosaur was collapsing beside the door. “This is either brilliant or the worst idea we’ve ever had.” Molly tugged on her gloves. “Bill, those are never different.” He hoisted the empty box. “After you, partner.” “Stealthily,” she said. “Of course,” Bill said, “for the children.”
created_at
"2026-03-18T11:18:00.648Z"
3/18/2026, 11:18:00 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2640
moderation_latency
(null)
generation_time
2811
tokens_prompt
77
tokens_completion
508
native_tokens_prompt
66
native_tokens_completion
369
native_tokens_completion_images
0
native_tokens_reasoning
65
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
0.00171
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_039e6b0fe36227080169ba89e8b6b48195a8181e0944f4be2f"
is_byok
false
latency
105
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-1773832680-VLUYSl2svHVXb1ywfH1x"
upstream_id
"resp_039e6b0fe36227080169ba89e8b6b48195a8181e0944f4be2f"
total_cost
0.00171
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
201
28.41%
Dialogue to Total Word Ratio
Ratio: 60.59%, Deviation: 10.59%
neededClean
false
wordsTotal
203
wordsDialogue
123
64.2069%