NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM09GAREXP2DFZ3HZZVW3D66
Run Details
Model:
GPT-5.4 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2.0s
Cost:
$0.001453
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
38.25%
Dialogue to Total Word Ratio
(details)
69.1179%
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, remember the plan?” Molly whispered. “Of course,” Bill said. “We enter as balloon entertainers, distract the adults, and vanish with the presents.” Molly peered through the hedge. “That’s a terrible plan.” “It’s a classic plan,” Bill replied. “The classics endure.” A tinny chorus of children’s laughter drifted from the garden. Streamers fluttered over a bouncy castle. A clown was tying a giraffe balloon onto a lamppost. Molly adjusted her fake moustache. “You look like a lost peanut.” “Thank you,” Bill said. “It’s the least suspicious disguise I own.” “Your disguise is a hat with a feather.” “A very confident hat.” A mother in a glittery apron passed the gate carrying paper cups. Bill straightened. “We just need to get to the gift table.” “And then?” “And then,” Bill said, “we load the presents into the pram.” Molly stared. “The pram?” “It has wheels. It has cover. It is, tactically speaking, glorious.” A child shouted, “The magician is here!” Bill’s eyes widened. “We have a magician?” Molly grinned. “No, Bill. That’s you.” He inhaled. “I hate when your ideas improve mine.” “Smile,” she said, nudging him forward. “It’s a party.” “And a robbery,” Bill muttered. “Same thing,” Molly said, “if nobody notices.”
created_at
"2026-03-18T10:57:45.752Z"
3/18/2026, 10:57:45 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
395
moderation_latency
(null)
generation_time
1879
tokens_prompt
77
tokens_completion
388
native_tokens_prompt
66
native_tokens_completion
312
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
0.0014535
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_02d75cbd2346176a0169ba8529d1748194b47356246ceb0f76"
is_byok
false
latency
216
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-1773831465-W2yFh9iOZ5g2sk4eHx4f"
upstream_id
"resp_02d75cbd2346176a0169ba8529d1748194b47356246ceb0f76"
total_cost
0.0014535
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
202
38.25%
Dialogue to Total Word Ratio
Ratio: 59.90%, Deviation: 9.90%
neededClean
false
wordsTotal
202
wordsDialogue
121
69.1179%