NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAJNQ9TSDRP79V837Q9M14
Run Details
Model:
GPT-5 Nano
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
2m 3s
Cost:
$0.005612
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 crouch behind a snack table, whispering plans.) (A stray balloon drifts by, tugging at a streamer.) (They grin softly.) Molly: We’ll enter as guests, compliment the cake, and pretend our mission is to collect the giggles and glitter tonight. Bill: Great, we’ll blend with balloons, practice our most innocent faces, and casually pocket everything wrapped in shiny paper tonight. Molly: I’ll corner the gift tables while you distract the clowns with a dramatic sneeze and a credit card trick. Bill: A sneeze will do, but I’m more comfortable with a sneeze-and-tiptoe routine, synchronized with the giggling security camera tonight. Molly: Remember the exit route, not a door, a suggestion of escaping through an enthusiastic group hug from the crowd. Bill: If anything goes sideways, we deploy the decoy cake and pretend we’re part of the dessert committee tonight anyway. Molly: Then we bow, exit, and pretend the night belonged to the magic in the frosting and the squeaky shoes. Bill: If we’re questioned, we claim it was an elaborate performance for charity sponsored by a very forgetful elf tonight. Molly: Agreed, partner; our tale ends with cupcakes, not cuffs, and a bow to the toddlers who unknowingly applauded us.
created_at
"2026-02-16T13:37:02.915568+00:00"
2/16/2026, 1:37:02 PM
model
"openai/gpt-5-nano-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3742
moderation_latency
(null)
generation_time
122642
tokens_prompt
77
tokens_completion
1750
native_tokens_prompt
66
native_tokens_completion
14022
native_tokens_completion_images
0
native_tokens_reasoning
13696
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
0.0056121
router
(null)
provider_responses
0
id
"resp_035b15c8d955cfa40169931d03e3748195bac9084f054167c1"
status
200
is_byok
false
latency
114
endpoint_id
"50329d77-04e1-4979-a184-c33030289476"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-nano-2025-08-07"
api_type
"completions"
id
"gen-1771248899-J3DgPRuVJ9fKEqZFJxxg"
upstream_id
"resp_035b15c8d955cfa40169931d03e3748195bac9084f054167c1"
total_cost
0.0056121
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
0.0000%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 90.00%
neededClean
false
wordsTotal
202
wordsDialogue
0
49.9920%