NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKA2S5MAMW47ZZPF5KTTSYD
Run Details
Model:
GPT-5 Nano
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
59.4s
Cost:
$0.002277
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
Behind a hedge, Molly whispered. Molly: The party at Maple Street School is perfect for presents. Bill: Perfectly chaotic, like their punch bowls and balloons. Molly: We’ll slip in during cake time, when the chaos is loudest. Bill: And the presents will be begging for mercy, if wrapping could talk. Molly: Step one: blend in. Talk like you belong. Bill: I belong to the snack table. I’m a professional snack critic. Molly: Step two: locate the loot without waking the chaperones. Bill: Loot? Glittery treasure chests, stacks of ribbons, sock puppets? I’m in. Molly: Step three: swap nothing, carry everything, run. Bill: Run where? To the car or to the moon? Molly: The car. The moon is too public. Bill: What about alarms? Molly: Ignore them. We’ll pretend we’re lost parents hunting the perfect birthday kite. Bill: A kite is a perfect cover. Kites don’t need batteries or cops. Molly: Remember, we’re pro-level pranksters, not burglars. We want chaos, not harm. Bill: Chaos gets you cake. Cake makes people suspicious. Molly: We’ll leave a trail of red noses and confetti as a decoy. Bill: Decoy accepted. Then we vanish, like missing glitter. Molly: On three: one, two, three. Bill: Go!
created_at
"2026-02-16T13:27:19.013233+00:00"
2/16/2026, 1:27:19 PM
model
"openai/gpt-5-nano-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9930
moderation_latency
(null)
generation_time
59120
tokens_prompt
77
tokens_completion
1206
native_tokens_prompt
66
native_tokens_completion
5685
native_tokens_completion_images
0
native_tokens_reasoning
5376
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
0.0022773
router
(null)
provider_responses
0
id
"resp_044fc6581d97940b0169931afb25c48195b119830c742f872d"
status
200
is_byok
false
latency
120
endpoint_id
"50329d77-04e1-4979-a184-c33030289476"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-nano-2025-08-07"
api_type
"completions"
id
"gen-1771248379-BxruTLcqbsWMONjY9YuO"
upstream_id
"resp_044fc6581d97940b0169931afb25c48195b119830c742f872d"
total_cost
0.0022773
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
words
200
0.0000%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
200
wordsDialogue
0
50.0000%