NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX3ZZ41G76M2V4M1S0NZD6BS
Run Details
Model:
GPT-5.6 Terra
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
5.5s
Cost:
$0.004740
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
49.78%
Dialogue to Total Word Ratio
(details)
72.8846%
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 bungalow’s balloons with professional suspicion. Pink streamers drooped from the porch like exhausted flamingos. Through the window, eight children shrieked around a magician whose cape appeared to be made from a tablecloth. Bill adjusted his black wool mask. It had eyeholes, a mouth hole, and, regrettably, a label reading MUM’S GOOD SCARF. “We wait for cake,” Molly whispered. “Why cake?” “Because frosting causes chaos. Tiny fingers, poor coordination, sugar-fueled betrayal.” On the lawn, a pirate piñata swayed above a cluster of foam swords. Bill checked the blueprint: kitchen window, hallway, gift mountain, exit via garden shed. The plan had been elegant before Molly noticed the inflatable unicorn blocking the gate. “We’re stealing presents from children,” Bill muttered. “We’re redistributing luxury plastic to the secondary market.” A boy in a dinosaur costume opened the back door and released a terrier wearing a bow tie. The dog spotted them immediately, barked once, then trotted over carrying a squeaky banana. Molly froze. Bill accepted the banana solemnly. “Bribed?” “Recruitment attempt,” Molly said. Inside, the magician produced a rabbit. Every child screamed with delight except one, who pointed at the hedge. “Are those burglars?” Molly rose, clutching the banana. “No,” she called. “We’re the entertainment.”
created_at
"2026-07-09T17:49:18.942Z"
7/9/2026, 5:49:18 PM
model
"openai/gpt-5.6-terra-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
484
moderation_latency
(null)
generation_time
5157
tokens_prompt
77
tokens_completion
390
native_tokens_prompt
66
native_tokens_completion
305
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
0.00474
router
(null)
provider_responses
0
endpoint_id
"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id
"resp_0123720aad420331016a4fdf1f112081968930229645ca6637"
is_byok
false
latency
252
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-1783619358-dW0TAaE8Dt5Bbhv7ZDCe"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783619358-uhrgFuMAOm54PjoZZXWB"
upstream_id
"resp_0123720aad420331016a4fdf1f112081968930229645ca6637"
total_cost
0.00474
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
95.99%
Matches word count
n/a
neededClean
false
words
208
49.78%
Dialogue to Total Word Ratio
Ratio: 19.14%, Deviation: 9.14%
neededClean
false
wordsTotal
209
wordsDialogue
40
72.8846%