NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM082T64PHGZH6CNAAXW3VN5
Run Details
Model:
GPT-5.4 Mini (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.8s
Cost:
$0.006255
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
23.13%
Dialogue to Total Word Ratio
(details)
61.5643%
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 pressed her ear to the bakery wall. “Bill, tell me you’ve brought the cart.” “Of course I’ve brought the cart,” Bill whispered. “What sort of professional thief do you take me for?” “The kind who once tried to rob a locked picnic basket.” “That basket was vicious.” “Did it have guard dogs?” “Two geese. Worse.” Molly peered around the corner. “The party starts in ten minutes.” “Excellent,” Bill said. “Children arrive with presents, parents arrive with cake, and we arrive with the moral flexibility.” “That’s not a phrase.” “It is if you say it confidently.” She grinned. “We take the gifts, vanish through the side gate, and leave behind the decoy?” “The decoy clown?” “The decoy clown.” Bill shuddered. “I still hate that clown.” “Everyone hates that clown. That’s why he’s perfect.” “You’re sure this is legal?” “Bill, we are thieves.” “Right. Silly question.” A horn sounded inside the hall. “Cupcake alarm,” Molly said. “Then let’s be terrible people in a very punctual way.” She offered her hand. “Ready?” He clasped it. “Ready.” “Remember,” Molly said, “if anyone asks, we were hired entertainment.” Bill nodded. “What kind?” “The vanishing kind.” “Perfect,” Bill said. “I’ve always wanted applause and pockets.”
created_at
"2026-03-18T10:32:54.226Z"
3/18/2026, 10:32:54 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5264
moderation_latency
(null)
generation_time
5595
tokens_prompt
77
tokens_completion
378
native_tokens_prompt
66
native_tokens_completion
1379
native_tokens_completion_images
0
native_tokens_reasoning
1076
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
0.006255
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_035af0a9abb5f61c0169ba7f564cf48194adbc8a0eb0839da1"
is_byok
false
latency
207
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-1773829974-2myuzWoArcDlRkxr33RU"
upstream_id
"resp_035af0a9abb5f61c0169ba7f564cf48194adbc8a0eb0839da1"
total_cost
0.006255
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
23.13%
Dialogue to Total Word Ratio
Ratio: 79.00%, Deviation: 11.00%
neededClean
false
wordsTotal
200
wordsDialogue
158
61.5643%