NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9FJSWVP92PEMGHX3HDMMN
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
40.7s
Cost:
$0.008339
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
The party smelled of frosting and chaos, a perfect chaos for two amateurs with imaginations larger than their criminal records. Molly crouched behind a table draped in cartoon streamers, rehearsing excuses she would never use. Bill balanced a stolen balloon on his shoulder like a nervous sentinel, whispering about timing and timing alone while his knees bounced to the music. They weren’t professionals; their plans were bedtime stories with sticky fingerprints. Molly said, "We distract them with cake, then nab the gifts quickly." Bill replied, "I'm in. Costumes? Maybe a clown, maybe a magician later." They smiled like conspirators and immediately argued about the ethics of stealing from confetti-covered toddlers. It was less about greed than the thrill, the ridiculousness of two grown people attempting to outwit cupcakes and balloons. A toddler waved a sparkly wand and declared them heroes. For a second they almost believed it, plotting absurdities that sounded like party games. They practiced solemn nods and secret handshakes, rehearsing improbable alibis involving glitter, misplaced cupcakes, and a hammy, off-key rendition of 'Happy Birthday' to explain everything later. Outside, the streetlamp winked; inside, the party could not possibly be a better target for bad decisions and good intentions.
created_at
"2026-02-16T13:16:31.026317+00:00"
2/16/2026, 1:16:31 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6038
moderation_latency
(null)
generation_time
40567
tokens_prompt
77
tokens_completion
1104
native_tokens_prompt
66
native_tokens_completion
4161
native_tokens_completion_images
0
native_tokens_reasoning
3840
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
0.0083385
router
(null)
provider_responses
0
id
"resp_0587cb4177d6583d01699318860434819080764a7dd0cada8a"
status
200
is_byok
false
latency
104
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771247749-YQxDpVUhmul7x7rGJpbk"
upstream_id
"resp_0587cb4177d6583d01699318860434819080764a7dd0cada8a"
total_cost
0.0083385
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
99.3226%
Dialogue to Total Word Ratio
Ratio: 12.87%, Deviation: 2.87%
neededClean
false
wordsTotal
202
wordsDialogue
26
99.6533%