NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0A28D4CVSMP4VHP3JT8AHT
Run Details
Model:
GPT-5.4 Mini (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
3.1s
Cost:
$0.001647
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
52.4451%
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 bakery dumpster, peering at the bright balloons bobbing over the garden wall. “There,” she whispered, “the birthday fortress.” Bill adjusted his borrowed clown nose. “I hate that you’re right. It’s too cheerful.” “Cheerful means distracted.” “It also means sticky.” A chorus of children shrieked from inside, followed by a trumpet of karaoke and the thump of a bouncy castle. Molly opened her satchel and checked the tiny toolkit. “We go in with confidence.” “Confidence?” Bill said. “I have soup on my cuff and a balloon animal in my hat.” “Perfect disguise. You look like a man who belongs at a party.” “I look like a man who lost a fight with a craft table.” Molly smiled despite herself. “Remember the plan. We mingle, locate the pile of presents, and exit before anyone notices the loot is gone.” “And if they ask questions?” “Smile, wave, and hand them a cupcake.” Bill blinked. “We’re stealing from children.” “We’re redistributing birthday abundance.” “That is the most criminal sentence I’ve ever heard.” Molly pressed her ear to the gate. “Ready?” Bill sighed, straightened his clown nose, and lifted the latch. “For the record, if we get caught, I’m blaming your process.” “Fine,” Molly said, stepping into the sugar-scented chaos. “But I’m carrying the presents.”
created_at
"2026-03-18T11:07:33.166Z"
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
2628
moderation_latency
(null)
generation_time
2942
tokens_prompt
77
tokens_completion
505
native_tokens_prompt
66
native_tokens_completion
355
native_tokens_completion_images
0
native_tokens_reasoning
49
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
0.001647
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0ac45f1249afaadd0169ba877541548194b9a1c5be34fcd920"
is_byok
false
latency
250
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-uOnM61jXL0oS7Hh2667r"
upstream_id
"resp_0ac45f1249afaadd0169ba877541548194b9a1c5be34fcd920"
total_cost
0.001647
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
214
36.79%
Dialogue to Total Word Ratio
Ratio: 60.00%, Deviation: 10.00%
neededClean
false
wordsTotal
215
wordsDialogue
129
52.4451%