NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9SRD69NMRXWZNV0NFY6K3
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
25.0s
Cost:
$0.005431
Provider:
OpenAI
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 peered through the party window, eyes glittering like cheap tinsel. Bill balanced a backpack that had seen more cake than daylight. Inside, balloons bobbed and a cacophony of sugar and plastic warred with lullabies. They whispered schemes the way conspirators whisper about weather, methodically, as if theft required weather reports. The plan hinged on a nap schedule and a distracted magician. Molly brushed a strand of hair and grinned. Molly: "We grab the cake, then the gifts." Bill grunted approval and adjusted his gloves. Bill: "And the piñata too, quietly." Outside, a garden gnome looked accusatory. They rehearsed exits like tango steps. Molly: "Exit through the clown door." The clown door, an emergency flap decorated with a smiling face, seemed to hope for applause. Bill checked his watch and smirked. Bill: "No confetti ever." They melted into shadow, sneakers whispering criminal lullabies. By the hedge, Molly hummed a nursery rhyme as if it were an incantation. Bill wiped frosting from his glove with unnecessary care. The moon signed off on the conspiracy, a silver spectator. They practiced polite theft—no rips, no tantrums—cataloguing toys by value and squeakiness while moonlight conducted their amateur orchestra and giggled like thieves in training.
created_at
"2026-02-16T13:21:48.808753+00:00"
2/16/2026, 1:21:48 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2475
moderation_latency
(null)
generation_time
24737
tokens_prompt
77
tokens_completion
1092
native_tokens_prompt
66
native_tokens_completion
2707
native_tokens_completion_images
0
native_tokens_reasoning
2368
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
0.0054305
router
(null)
provider_responses
0
id
"resp_09e413f418df83cb01699319d36e84819583b0fa511f67a37b"
status
200
is_byok
false
latency
123
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771248083-mVzawbahok9pSxQH9KIl"
upstream_id
"resp_09e413f418df83cb01699319d36e84819583b0fa511f67a37b"
total_cost
0.0054305
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9840%
Matches word count
n/a
neededClean
false
words
202
100.0000%
Dialogue to Total Word Ratio
Ratio: 9.90%, Deviation: 0.10%
neededClean
false
wordsTotal
202
wordsDialogue
20
99.9920%