NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX40VVMS3QYJKV3EAW0NK9X6
Run Details
Model:
GPT-5.6 Terra
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5.6s
Cost:
$0.004935
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
35.41%
Dialogue to Total Word Ratio
(details)
58.3429%
Overall
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 crouched behind the hedge, studying the bungalow’s balloon-festooned windows. Inside, children shrieked around a magician who appeared deeply regrettable. “Count the presents,” Bill whispered. “I count twelve boxes, three bags, and one suspiciously flat dinosaur.” “Could be a skateboard.” “Could be a child folded incorrectly.” Bill adjusted his black ski mask. It had tiny unicorns on it. “Why are you wearing that?” “Camouflage.” “Against what, a rainbow burglary squad?” “Children trust unicorns.” “Children also bite.” From inside came a roar of applause, followed by the magician yelling, “No, that was my good dove!” Bill peered through the hedge. “The parents are in the kitchen. Cake deployment in two minutes.” “Excellent. We enter through the side gate, cross the patio, grab the loot, and leave before anyone notices.” “What about the dog?” Molly glanced at the dachshund wearing a paper crown. “He’s distracted by existential humiliation.” Bill produced a sack. “I brought wrapping paper.” “To steal presents?” “To rewrap them after.” “That is either considerate or deranged.” “Why not both?” A child pressed against the window, staring directly at them. “Bill,” Molly hissed, “don’t move.” “Why?” “He’s seen us.” The child waved. Bill waved back. “Now he thinks we’re entertainers.” Molly sighed. “Fine. You’re the unicorn. I’m the evil aunt. On three.”
created_at
"2026-07-09T18:05:00.452Z"
7/9/2026, 6:05:00 PM
model
"openai/gpt-5.6-terra-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
542
moderation_latency
(null)
generation_time
5395
tokens_prompt
77
tokens_completion
435
native_tokens_prompt
66
native_tokens_completion
318
native_tokens_completion_images
0
native_tokens_reasoning
0
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"
service_tier
"default"
usage
0.004935
router
(null)
provider_responses
0
endpoint_id
"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id
"resp_0d1edf7e38746098016a4fe2cc91b08190ac80e8b46fb8d2c2"
is_byok
false
latency
239
model_permaslug
"openai/gpt-5.6-terra-20260709"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1783620300-p57WEiIYKa533fw9DVxY"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620300-zbABCMS8SEyQWmKxWfaD"
upstream_id
"resp_0d1edf7e38746098016a4fe2cc91b08190ac80e8b46fb8d2c2"
total_cost
0.004935
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
212
35.41%
Dialogue to Total Word Ratio
Ratio: 60.09%, Deviation: 10.09%
neededClean
false
wordsTotal
213
wordsDialogue
128
58.3429%