NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KK9QD1ETK1F5GB3EKJ3NVRRH
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
29.4s
Cost:
$0.025275
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 hedge outside Number Twelve, studying the garden where balloons bobbed like surveillance blimps and a paper banner announced HENRY IS SIX with the confidence of a military parade. Bill, wearing a stolen magician’s cape and the expression of a man betrayed by glitter, unfolded the hand-drawn map of the patio, cake table, and suspiciously alert bouncy castle. From inside came the shriek of children, the bark of a terrier in a bow tie, and the bass thump of party music heroic enough for a bank robbery. “Tiny chairs, tiny guards; the presents will practically arrest themselves,” Molly murmured. “Distract the clown, praise the pony, then run like uncles,” Bill replied. They watched a princess hand a juice box to a pirate, while three parents argued over charcoal and one grandmother patrolled the gift table like a retired prison warden. The loot sat in a mountain of wrapping paper, ribbons, and optimistic plastic, every parcel tagged in cheerful handwriting. Molly adjusted her black gloves. Bill adjusted his fake moustache. Somewhere, a piñata swung in the breeze like a warning from the gods. Still, opportunity wore a party hat. And both thieves felt absurdly noble about the business.
created_at
"2026-03-09T16:38:06.052Z"
3/9/2026, 4:38:06 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
26891
moderation_latency
(null)
generation_time
29269
tokens_prompt
77
tokens_completion
316
native_tokens_prompt
66
native_tokens_completion
1674
native_tokens_completion_images
0
native_tokens_reasoning
1411
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
0.025275
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0ccd507b5503ca6e0169aef76e278481948dfef8fa3b3f196d"
is_byok
false
latency
245
model_permaslug
"openai/gpt-5.4-20260305"
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-1773074286-zYPaIWf6572gQNQKTKy2"
upstream_id
"resp_0ccd507b5503ca6e0169aef76e278481948dfef8fa3b3f196d"
total_cost
0.025275
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
100.00%
Dialogue to Total Word Ratio
Ratio: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
20
100.0000%