NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX418RK82XKZD0S446CG47PG
Run Details
Model:
GPT-5.6 Terra
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4.6s
Cost:
$0.004350
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
84.33%
Dialogue to Total Word Ratio
(details)
90.9792%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 studied the bungalow through binoculars disguised as a pair of novelty birthday glasses. Streamers fluttered over the garden gate, and a plastic unicorn guarded the driveway with the confidence of a minor deity. Bill unfolded the floor plan, which was actually a crayon drawing stolen from the birthday child’s fridge. The kitchen was marked “CAKE,” the living room “PRESENT MOUNTAIN,” and the upstairs bathroom “NO GROWNUPS.” “Timing?” Molly whispered. “Three fifteen,” Bill said. “The magician produces a rabbit. Everyone screams.” Inside, children chased bubbles while parents clustered near a table of suspiciously cheerful sandwiches. A woman in a crown distributed paper hats. Somewhere, a recorder played “Happy Birthday” with the grim determination of a haunted carousel. Molly adjusted her black gloves, decorated with tiny dinosaurs. “We take the gifts, leave the wrapping?” Bill considered this. “Leave one. A lesson in scarcity.” They slipped through the side gate, stepping around a paddling pool full of inflatable sharks. Bill froze when a toddler spotted them through the window. The toddler raised a juice box. Molly raised hers back. “Cover identity?” Bill murmured. “Party entertainers,” she said. Bill produced two balloon animals from his coat. They were both vaguely snakes. The toddler nodded solemnly and returned to eating icing.
created_at
"2026-07-09T18:12:03.31Z"
7/9/2026, 6:12:03 PM
model
"openai/gpt-5.6-terra-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
402
moderation_latency
(null)
generation_time
4507
tokens_prompt
77
tokens_completion
380
native_tokens_prompt
66
native_tokens_completion
279
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
0.00435
router
(null)
provider_responses
0
endpoint_id
"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id
"resp_0fa60c8085e1c9a7016a4fe473613081908ec2209c3d16780c"
is_byok
false
latency
193
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-1783620723-8mlvCVJ1ItJELSk3LhDM"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620723-6BIj48jsbJ95YK3nI9Ea"
upstream_id
"resp_0fa60c8085e1c9a7016a4fe473613081908ec2209c3d16780c"
total_cost
0.00435
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
97.63%
Matches word count
n/a
neededClean
false
words
207
84.33%
Dialogue to Total Word Ratio
Ratio: 16.43%, Deviation: 6.43%
neededClean
false
wordsTotal
207
wordsDialogue
34
90.9792%