NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PCJSAPP48RREBX030HSPK
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.6s
Cost:
$0.015690
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
97.70%
Dialogue to Total Word Ratio
(details)
82.9033%
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 café table. “Bill, behold: the birthday perimeter.” “That’s a placemat.” “It’s tactical stationery. Here’s the cake, here’s the clown, here’s the mountain of presents.” “Why is the clown labeled ‘possible wizard’?” “Because he made three sausages disappear.” “Children ate them, Molly.” “Exactly what a wizard would want us to think.” Bill squinted. “Our disguises?” “I’m going as Aunt Linda.” “You’re thirty-two.” “Aunt Linda is a state of mind.” “And me?” “You’re Balloon Man.” “I don’t know balloons.” “Perfect. Children respect mystery.” Bill tapped the map. “We stroll in, grab the gifts, stroll out?” “No. We mingle first. We compliment the piñata. We sing badly enough to be authentic.” “What if someone asks whose side we’re on?” “We say, ‘The birthday side.’ Works at every party.” Bill sighed. “Molly, stealing from children feels low.” “They’re not children’s presents yet. They’re wrapped potential.” “That is not a legal category.” “It is in my heart.” A waiter arrived. “More tea?” Bill said, “Please. And maybe a conscience.” Molly folded the placemat. “Fine. We’ll steal only the magician’s sausages.” “Now that’s a heist.”
created_at
"2026-04-24T21:29:59.855Z"
4/24/2026, 9:29:59 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6321
moderation_latency
(null)
generation_time
11549
tokens_prompt
77
tokens_completion
398
native_tokens_prompt
66
native_tokens_completion
512
native_tokens_completion_images
0
native_tokens_reasoning
221
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
0.01569
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0705143bb81759450169ebe0d7fa98819498a4a23b30c9560a"
is_byok
false
latency
283
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-1777066199-Ctro3T8BIc9NI0v9Av3y"
session_id
(null)
api_type
"completions"
id
"gen-1777066199-xrFIHN09ZSXqO8P1U7SY"
upstream_id
"resp_0705143bb81759450169ebe0d7fa98819498a4a23b30c9560a"
total_cost
0.01569
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
68.10%
Matches word count
n/a
neededClean
false
words
186
97.70%
Dialogue to Total Word Ratio
Ratio: 86.10%, Deviation: 3.90%
neededClean
false
wordsTotal
187
wordsDialogue
161
82.9033%