NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKB61SAV1D6GZ3B95GXZNE5
Run Details
Model:
GPT-5 Mini
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
44.5s
Cost:
$0.006326
Provider:
OpenAI
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 the cake table, whispering like conspirators. Molly: We go in during the cake or during the song? Bill: Cake, obviously. Cake creates chaos and frosting creates fingerprints. Molly: What about balloons? Balloons are noisy but useful for cover. Bill: We need tiny gloves, a map of presents, and a distraction—singing elf. Molly: I'll bring glitter. Glitter gets in everything and everyone blames toddlers. Bill: Convince the mom to open the closet; we'll swap the big boxes for decoys. Molly: What about the puppy? The puppy will chase us and ruin the plan. Bill: Bribe the puppy with a squeaky toy. Also bypass the piñata schedule. Molly: What if a toddler recognizes you from last Christmas? You had chocolate on your shirt. Bill: I burn everything, remember? Chocolate alibi, but bring napkins and a tiny wrench. Molly: Tiny wrench? What are you dismantling, a crib or a cookie jar? Bill: Cookie jar, obviously. We slip gifts into laundry baskets labeled "donations." Molly: What if kids ask for presents? Do we explain we're "Santa's interns"? Bill: Yes. Wear elf hats, mumble nonsense, and exit with confetti cannons. Molly: Timing, Bill. Five minutes after cake, sprint, no witnesses, full sacks.
created_at
"2026-02-16T13:46:19.864109+00:00"
2/16/2026, 1:46:19 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4956
moderation_latency
(null)
generation_time
44091
tokens_prompt
77
tokens_completion
1166
native_tokens_prompt
66
native_tokens_completion
3155
native_tokens_completion_images
0
native_tokens_reasoning
2816
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
0.0063265
router
(null)
provider_responses
0
id
"resp_08cbdff519ff0d920169931f7ed8d48195a3359beac4fdf15b"
status
200
is_byok
false
latency
139
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771249534-nq6i0YnBAJRlNOgOYuAh"
upstream_id
"resp_08cbdff519ff0d920169931f7ed8d48195a3359beac4fdf15b"
total_cost
0.0063265
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: 1.49%, Deviation: 88.51%
neededClean
false
wordsTotal
201
wordsDialogue
3
49.9995%