NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAMC0113WRJGFKFJBTMAY5
Run Details
Model:
GPT-5.1
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
30.1s
Cost:
$0.023563
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: A children’s party, Bill. We’ve finally hit moral rock bottom." "Bill: Nonsense. Kids have too much joy. We’re just redistributing birthday inequality." "Molly: You’re stealing unicorn puzzles from toddlers." "Bill: Unicorn puzzles build unrealistic expectations. I’m basically a life coach." "Molly: Philosophical kleptomania. Lovely. What’s the plan?" "Bill: We blend in as entertainment. I juggle, you do face painting, we liberate the presents." "Molly: My artistic ability peaks at stick figures." "Bill: Perfect. Nothing distracts parents like a tragically bad tiger on their child’s forehead." "Molly: And while they’re consoling the weeping tiger, we swipe the loot?" "Bill: Exactly. You swap gift bags with our decoy sack, I wheel the real one out." "Molly: What if some kid guards the pile like a sugar‑crazed dragon?" "Bill: Then you tell them there’s a piñata emergency." "Molly: That’s not a thing." "Bill: It is when you shout ‘The candy is endangered!’" "Molly: I can’t decide if this is genius or a cry for help." "Bill: Think of the resale value on twelve remote‑control cars." "Molly: And the guilt?" "Bill: Optional accessory. Sold separately." "Molly: Fine. But I’m keeping any stuffed sloth." "Bill: Deal. Even thieves have standards." "Molly: Especially about sloths."
created_at
"2026-02-16T13:36:26.181703+00:00"
2/16/2026, 1:36:26 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
27699
moderation_latency
(null)
generation_time
29899
tokens_prompt
77
tokens_completion
373
native_tokens_prompt
66
native_tokens_completion
2348
native_tokens_completion_images
0
native_tokens_reasoning
2025
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
0.0235625
router
(null)
provider_responses
0
id
"resp_06c29c0c517c64540169931d3b7ecc8196a7b6bfbe1322927c"
status
200
is_byok
false
latency
168
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771248955-KjQpxPmOmyT9yfnJf2Ma"
upstream_id
"resp_06c29c0c517c64540169931d3b7ecc8196a7b6bfbe1322927c"
total_cost
0.0235625
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
words
200
36.7879%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
200
wordsDialogue
200
68.3940%