NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKANHEDZCE9Y8H5A56PS0QD
Run Details
Model:
GPT-5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
43.9s
Cost:
$0.028762
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
Behind the inflatable castle, Molly adjusted her ski mask covered in cartoon unicorns. "This is morally questionable, even for us," she whispered. Bill peeked around plastic jungle vines strung from the patio pergola. "We're liberating the toys from capitalistic wrapping paper," he said. Somewhere inside, a magician shouted about friendship while balloons screamed against the ceiling. "Besides, kids forget half their presents by Tuesday," Molly muttered. Bill unfolded a crayon-drawn map they had stolen from the refrigerator earlier. "Entry point: clown bathroom window," he declared. A gust of cotton-candy-scented wind fluttered the flimsy paper, smearing blue giraffes into abstract art. "What if the clown is in there?" she asked. Bill shrugged, the movement making his sequined burglar jacket glitter accusingly beneath the porch light. "Then we improvise and steal his nose too," Bill replied. The bouncing castle groaned ominously, like a guilty conscience. "Okay, operation Birthday Heist begins: grab the loot, avoid frosting, and if anyone cries, we blame the mysterious Gift Goblin, not our beautiful criminal hearts this fine evening." "And remember, Bill, if a five-year-old tackles you, you go down, you stay down, and you compliment their ferocity while I stuff gifts into the getaway stroller of destiny."
created_at
"2026-02-16T13:37:18.116205+00:00"
2/16/2026, 1:37:18 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
31261
moderation_latency
(null)
generation_time
43737
tokens_prompt
77
tokens_completion
893
native_tokens_prompt
66
native_tokens_completion
2868
native_tokens_completion_images
0
native_tokens_reasoning
2585
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
0.0287625
router
(null)
provider_responses
0
id
"resp_0905937af82fcf2c0169931d61d0c4819093d28b1864c7cce5"
status
200
is_byok
false
latency
164
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771248993-ezDs6jbCfib5jN3NJOBR"
upstream_id
"resp_0905937af82fcf2c0169931d61d0c4819093d28b1864c7cce5"
total_cost
0.0287625
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
99.3769%
Matches word count
n/a
neededClean
false
words
205
100.0000%
Dialogue to Total Word Ratio
Ratio: 49.76%, Deviation: 0.24%
neededClean
false
wordsTotal
205
wordsDialogue
102
99.6885%