NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0MS6NGR7YWCRDWHENVEG6T
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
23.7s
Cost:
$0.040800
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
96.27%
Dialogue to Total Word Ratio
(details)
97.8223%
Overall
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 unfolded a crayon map on the bakery table. “Observe, Bill: the fortress. Bouncy castle, face-painting witch, and twelve sticky guards under four feet tall.” “Those guards bite.” “Only if you’re shaped like cake.” “I’m shaped like regret and sausage rolls.” “Perfect disguise. You’ll go in as Uncle Bill, professional balloon disappointment.” “Do I need balloons?” “No, that’s why you’re disappointing.” “And you?” “I’ll be Molly the Magnificent, hired magician. While I shout ‘abracadabra,’ you collect the presents.” “All of them?” “All. Teddy bears, robots, suspiciously book-shaped parcels.” “What about the birthday child?” “We leave a note: ‘Your gifts have been liberated by artists.’” “That’s not a note, that’s a villain’s confession.” “Fine. ‘Rain check.’” “Molly, children remember faces. Especially faces that steal scooters.” “Then wear the clown nose.” “I swore never again after the christening.” “You sneezed glitter into a vicar. History applauds.” “Suppose the parents stop us?” “Distract them with the phrase ‘educational puppet show.’ Adults flee learning.” “And if the kids chase us?” “Throw cupcakes.” “That’s cruel.” “Gluten-free cupcakes.” “Right. Nobody will follow.” Bill sighed. “We are monsters.” “Entrepreneurial monsters. Now practice saying, ‘Who wants balloon taxes?’ without weeping near the piñata.”
created_at
"2026-04-24T21:01:56.281Z"
4/24/2026, 9:01:56 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
22663
moderation_latency
(null)
generation_time
23139
tokens_prompt
77
tokens_completion
950
native_tokens_prompt
66
native_tokens_completion
1349
native_tokens_completion_images
0
native_tokens_reasoning
1034
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.0408
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0383c0b8c2bded030169ebda4463a4819491db6684f64cf340"
is_byok
false
latency
306
model_permaslug
"openai/gpt-5.5-20260423"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777064516-qIYqTMwIw9TYrMfRuqlo"
session_id
(null)
api_type
"completions"
id
"gen-1777064516-Ok3l1flUNwy72OHMffJr"
upstream_id
"resp_0383c0b8c2bded030169ebda4463a4819491db6684f64cf340"
total_cost
0.0408
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
195
96.27%
Dialogue to Total Word Ratio
Ratio: 94.42%, Deviation: 4.42%
neededClean
false
wordsTotal
197
wordsDialogue
186
97.8223%