NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9KDJXJKQAVANDCSSNYF61
Run Details
Model:
GPT-5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
2m 19s
Cost:
$0.075773
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
Molly spread the map across the sticky diner table. Crayon arrows looped between doodled balloons, cake, and gift mountain. Bill, still wearing his burglar mask like a beanie, squinted. "So, entry point: we crash the party disguised as magicians." Outside, rain slapped the window, drumming a dramatic, unnecessary soundtrack. "Magicians steal attention, not property; I prefer invisible cupcake inspectors." "Cupcake inspectors wear hairnets, Bill; do I look responsible today?" The target was not a bank vault or museum tonight. "Fine, we’re balloon artists, specializing in complex emotionally unstable giraffes." It was a suburban birthday extravaganza for eight hyperactive second-graders. "While children argue over giraffes, you liberate the presents, gracefully." Glitter cannons, a rented pony, and an ominous professional clown. "Define liberate; time it meant running, screaming, covered in glitter." "Glitter is tactical; parents track sparkling footprints, not missing parcels." Also, according to Molly’s notes, an unreasonable number of presents. "What about the clown, Molly; he smells fear and debt." Bill traced a path through scribbled sprinkles with a fork. "I juggle his shoes; distracted, barefoot, he’s emotionally disarmed, obviously." The waitress walked past, glanced, and decided not to ask. "If musical chairs starts, we bail, presents first, dignity later." Planning.
created_at
"2026-02-16T13:20:15.330281+00:00"
2/16/2026, 1:20:15 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
43088
moderation_latency
(null)
generation_time
139152
tokens_prompt
77
tokens_completion
1278
native_tokens_prompt
66
native_tokens_completion
7569
native_tokens_completion_images
0
native_tokens_reasoning
7249
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
0.0757725
router
(null)
provider_responses
0
id
"resp_093361169ea824d00169931903bff481938cbb8331a36340d7"
status
200
is_byok
false
latency
142
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771247875-RUKJ7a99qWVvjCntWTdt"
upstream_id
"resp_093361169ea824d00169931903bff481938cbb8331a36340d7"
total_cost
0.0757725
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
100.0000%
Dialogue to Total Word Ratio
Ratio: 49.75%, Deviation: 0.25%
neededClean
false
wordsTotal
201
wordsDialogue
100
99.9995%