NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX40PBVGHN6WCV6FR7YG1N55
Run Details
Model:
GPT-5.6 Terra
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
4.6s
Cost:
$0.004365
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
99.81%
Dialogue to Total Word Ratio
(details)
98.7208%
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 crouched behind the hedge, studying the birthday house with professional suspicion. Balloons bobbed on the gate like brightly colored witnesses. Through the window, children shrieked around a magician whose cape appeared to be made from a tablecloth. Bill adjusted his black ski mask, which had tiny embroidered kittens on it. “Why are there twelve parents in there?” Molly whispered. “Security,” Bill said. “Hostile security with juice boxes.” On the dining table sat a mountain of presents: wrapped cubes, shiny bags, one enormous parcel shaped like a dinosaur. Molly’s fingers twitched. Their fence had promised excellent resale value, especially for anything requiring batteries. The plan was simple. Bill would trigger the garden sprinkler, sending adults outside in a damp, panicked stampede. Molly would slip through the back door, load the gifts into a laundry basket, and vanish through the neighbor’s compost alley. A clown wandered past the window, staring directly at them. Molly froze. “Is that clown watching us?” “He’s probably undercover,” Bill muttered. The sprinkler sputtered, coughed, then erupted with the enthusiasm of a municipal fountain. Parents surged outdoors, clutching paper plates and toddlers. Molly darted toward the door. Inside, the magician lifted his wand. Every present began to bark. Bill sighed. “I hate themed parties.”
created_at
"2026-07-09T18:02:00.439Z"
7/9/2026, 6:02:00 PM
model
"openai/gpt-5.6-terra-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
474
moderation_latency
(null)
generation_time
4547
tokens_prompt
77
tokens_completion
374
native_tokens_prompt
66
native_tokens_completion
280
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
0.004365
router
(null)
provider_responses
0
endpoint_id
"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id
"resp_00c6a0d80eb09860016a4fe21880348190a4a3f4f21e5b2737"
is_byok
false
latency
227
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-1783620120-ZSWgtn9SWO3OqxqWGgoS"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620120-PhujhcqmQ8LhsckpdkD1"
upstream_id
"resp_00c6a0d80eb09860016a4fe21880348190a4a3f4f21e5b2737"
total_cost
0.004365
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
99.81%
Dialogue to Total Word Ratio
Ratio: 12.08%, Deviation: 2.08%
neededClean
false
wordsTotal
207
wordsDialogue
25
98.7208%