NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKB1PR7XGRN8ECSE9A9ZPNH
Run Details
Model:
GPT-5 Nano
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
58.0s
Cost:
$0.003428
Provider:
OpenAI
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Moonlight slid over cul-de-sac as Molly checked her pocket map and Bill sharpened a joke on the tip of his tongue. A banner from the children's party fluttered through a window, reminding them of bats, balloons, and the unspoken rule of not waking the unicorns. They practiced their breezy, confident heist faces, then softened into conspiratorial grins. The plan unfolded with charm: enter through the lemonade stand, disable the garland alarm, replace the loot with decoy gifts, and exit via the fire escape while the pizza deliveries distracted the dogs. They whispered, counted steps, and pretended this was ordinary business. Molly: "We go in through the lemonade stand quietly tonight." Bill: "Relax, we move like balloons, soft and ridiculous tonight." Molly: "Keep the decoys ready and the dogs distracted outside." Bill: "Copy the plan, but improvise if the clown arrives." Molly: "Lure the partygoers with cupcakes, not glitter cannons tonight." Bill: "After the heist, we retire to the neighbor's yard." Molly: "Remember, no one should wake the birthday wizard inside." Bill: "I packed a cookie crumb map for exits tonight." Molly: "If anything blares, we tango with the drums outside." Bill: "Deals are done when the stars smile and fade."
created_at
"2026-02-16T13:44:11.101191+00:00"
2/16/2026, 1:44:11 PM
model
"openai/gpt-5-nano-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2829
moderation_latency
(null)
generation_time
57369
tokens_prompt
77
tokens_completion
1714
native_tokens_prompt
66
native_tokens_completion
8561
native_tokens_completion_images
0
native_tokens_reasoning
8256
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
0.0034277
router
(null)
provider_responses
0
id
"resp_051cbb2a05a1e2df0169931ef07ac88194a01727862b679c4a"
status
200
is_byok
false
latency
135
endpoint_id
"50329d77-04e1-4979-a184-c33030289476"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-nano-2025-08-07"
api_type
"completions"
id
"gen-1771249392-YjMUS9XmgsqHlsmDqfYf"
upstream_id
"resp_051cbb2a05a1e2df0169931ef07ac88194a01727862b679c4a"
total_cost
0.0034277
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
91.5820%
Dialogue to Total Word Ratio
Ratio: 44.55%, Deviation: 5.45%
neededClean
false
wordsTotal
202
wordsDialogue
90
95.7830%