NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAJEC6SJRXH24N04TYC7G2
Run Details
Model:
GPT-5 Nano
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 56s
Cost:
$0.005045
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
Under flickering streetlamps, Molly and Bill huddle, plotting a caper that smells suspiciously like bubbles and mischief in the air. Molly: Okay, think big but stay quiet, like ninjas tonight. Bill: Children's party cover, balloons and confetti, perfect distraction today. Molly: We drift in, past kitchen walls, like party mice. Bill: Then we charm sister with pockets of glow sticks. Molly: Glow sticks, red ribbons, napkin map, all comically useless. Bill: Napkin map is art, not instructions, obviously to us. Molly: Not useless if giggles guide us: left at cake. Bill: The cake fortress; frosting moats, sprinkles guards, glorious absurdity. Molly: We practice door etiquette, sneeze, steal all the presents. Bill: Also pretend pizza order; distraction is a tactic today. Molly: What if the mascot notices us, Bill, hmm, anyway. Bill: We dance with mascot; mischief royalties payable eventually, friend. Molly: And swap gifts with dragon boxes, glittering gambit tonight. Bill: Dragon boxes leave glitter trails; glitter is elegant escape. Molly: Promise we won't wake the teacups on table tonight. Bill: Deal; after, we celebrate with cocoa and medals together. Molly: If we succeed, the party will howl with joy. Bill: Then we vanish, leaving confetti as our alibi tonight.
created_at
"2026-02-16T13:36:48.473415+00:00"
2/16/2026, 1:36:48 PM
model
"openai/gpt-5-nano-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
7536
moderation_latency
(null)
generation_time
114932
tokens_prompt
77
tokens_completion
2152
native_tokens_prompt
66
native_tokens_completion
12603
native_tokens_completion_images
0
native_tokens_reasoning
12288
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
0.0050445
router
(null)
provider_responses
0
id
"resp_052d619f0eed421b0169931cfc613081909c92a1467019cb5f"
status
200
is_byok
false
latency
104
endpoint_id
"50329d77-04e1-4979-a184-c33030289476"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-nano-2025-08-07"
api_type
"completions"
id
"gen-1771248892-VVvrRFJvA0NjjWXgO5h8"
upstream_id
"resp_052d619f0eed421b0169931cfc613081909c92a1467019cb5f"
total_cost
0.0050445
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%