NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9QV9H9BGH16BAT51HDM24
Run Details
Model:
GPT-5 Nano
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
1m 14s
Cost:
$0.003032
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
Molly: Plan's perfect, Bill, the party's chaos will hide everything. Bill: Don't forget the confetti cannon distraction; it distracts children. Molly: We arrive dressed as volunteers, handing balloons, spreading smiles. Bill: Meanwhile, we scout the room for the best routes. Molly: If laughter erupts, we pretend we're totally entertaining tonight. Bill: Deal, and keep the faces innocent, like passing clowns. Molly: We only want the presents, not the party's aura. Bill: Plausible alibis help; we can say we misplaced cupcakes. Molly: Disguise ourselves as delivery elves, with oversized gift bags. Bill: Then we vanish in the bounce-house, into the night. Molly: I hear the cake's rainbow frosting; temptation will strike. Bill: Stay steady, McFuzz, your giggles might rally the guards. Molly: If we get spotted, improvise with improvised lullabies quickly. Bill: Lullabies distract parents; kids will adore the impromptu concert. Molly: Then we extract one glittering souvenir per bag only. Bill: Make sure nothing shatters; glitter travels worse than rumors. Molly: If any kid notices, compliment their manners, diffuse suspicion. Bill: Then we exit, a tornado of party whistles, gone. The alley shivers with stray giggles as they rehearse a prankish, utterly nonviolent caper for the grandchildren's amazement tonight happily.
created_at
"2026-02-16T13:21:34.98455+00:00"
2/16/2026, 1:21:34 PM
model
"openai/gpt-5-nano-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
16585
moderation_latency
(null)
generation_time
73544
tokens_prompt
77
tokens_completion
1208
native_tokens_prompt
66
native_tokens_completion
7571
native_tokens_completion_images
0
native_tokens_reasoning
7232
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
0.0030317
router
(null)
provider_responses
0
id
"resp_0633d6e778a42ded0169931994e578819386ee3936a3813262"
status
200
is_byok
false
latency
130
endpoint_id
"50329d77-04e1-4979-a184-c33030289476"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-nano-2025-08-07"
api_type
"completions"
id
"gen-1771248020-4oCKQjhb8xwzxOpeXmQ7"
upstream_id
"resp_0633d6e778a42ded0169931994e578819386ee3936a3813262"
total_cost
0.0030317
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: 90.00%
neededClean
false
wordsTotal
201
wordsDialogue
0
49.9995%