NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAJ9PTPB5F1NVRY2KEENGF
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
42.8s
Cost:
$0.008094
Provider:
OpenAI
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
They crouched behind a birthday banner, tinsel tickling their noses. Molly outlined the plan while Bill winked at a clown poster. Outside, carols, children shrieked, a parent lost a phone. The living room glowed with streamers and large teddy bears. They rehearsed silent footwork, decided on decoy gift placement, and practiced an improvised apology for toddlers. Their hands twitched for tape and ribbon like thieves reaching for familiar tools. Molly spotted a cake-safe window, Bill counted trunks of wrapping paper. They grinned at each other, the absurdity of the job punctuating their craft. This was professional ridiculousness they both loved. Molly: Let's steal cake, gifts, balloon animals, glitter, and confetti. Bill: Quiet, slick, no crying kids, grab presents, exit chimney. Molly: What about cake frosting fingerprints, Santa hat, suspicious adults? Bill: Gloves, hairnet, decoy gift, cat distraction, hurry, whisper, now Molly: Timing matters, cake smash at five, chaos gives cover. Bill: Route mapped, backdoor, toy chest, van with fake balloons. Molly: We take only wrapped presents, avoid unwrapped sentimental junk. Bill: Leave a note, signed Santa's helpers, glitter trail art. Molly: If toddlers scream, improvise with puppets and cookie diplomacy. Bill: Ready, Molly? One last check, breathe, grin, then go.
created_at
"2026-02-16T13:35:31.492933+00:00"
2/16/2026, 1:35:31 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4043
moderation_latency
(null)
generation_time
42478
tokens_prompt
77
tokens_completion
1382
native_tokens_prompt
66
native_tokens_completion
4039
native_tokens_completion_images
0
native_tokens_reasoning
3712
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
0.0080945
router
(null)
provider_responses
0
id
"resp_0e2759cbf1c4846c0169931cf7977c8194b0420ed2db4665e8"
status
200
is_byok
false
latency
52
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771248887-StZJYjTOaZdEsMVXa4Du"
upstream_id
"resp_0e2759cbf1c4846c0169931cf7977c8194b0420ed2db4665e8"
total_cost
0.0080945
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.9990%
Matches word count
n/a
neededClean
false
words
201
0.0000%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 50.00%
neededClean
false
wordsTotal
201
wordsDialogue
0
49.9995%