NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX41NY2VCCDDDEW68BRW7EFS
Run Details
Model:
GPT-5.6 Terra
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
5.4s
Cost:
$0.005130
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
43.76%
Dialogue to Total Word Ratio
(details)
52.0157%
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 balloons bobbing over the garden fence. A clown shaped like a carrot waved at nobody. “Children’s parties have layers,” Bill whispered. “Like cake?” “Like security. Cake is merely morale.” Molly adjusted her black gloves. “We’re stealing presents, not invading a fortress.” “The bouncy castle is a distraction unit. The magician is surveillance. And that pony knows things.” “It’s wearing a party hat, Bill.” “Exactly. Camouflage.” Inside, shrieking children chased bubbles while parents clustered around a table of suspiciously unattended prosecco. “Window’s open,” Molly said. “Gift pile is beside the sofa.” “Too obvious.” “That’s generally where presents go.” Bill produced a laminated floor plan. “We enter through the shed, cross the patio, neutralize the piñata, then—” “Neutralize it?” “It contains candy. Candy causes chaos.” Molly peered through the fence. “The birthday girl is six.” “Six-year-olds are unpredictable criminals.” A small boy spotted them. “Mum! There’s a lady in the bushes!” Molly smiled brightly. “We’re entertainers.” Bill sprang up. “I’m Professor Balloon!” “You’re wearing burglar black.” “Academic black.” The boy frowned. “Do you do tricks?” Bill grabbed a balloon from the hedge. “Observe. I make presents disappear.” Molly hissed, “That is exactly the trick we’re not announcing.” From the garden, the clown shouted, “Anybody seen the gift bags?” Bill bowed. “Showtime.”
created_at
"2026-07-09T18:19:14.915Z"
7/9/2026, 6:19:14 PM
model
"openai/gpt-5.6-terra-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
546
moderation_latency
(null)
generation_time
5199
tokens_prompt
77
tokens_completion
456
native_tokens_prompt
66
native_tokens_completion
331
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
0.00513
router
(null)
provider_responses
0
endpoint_id
"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id
"resp_038e288dd2e32491016a4fe62303848197be7279550d5da881"
is_byok
false
latency
237
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-1783621154-Ns9UJlHTorD0yyPaUr7I"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783621154-Og5NHnsgct46ZSLnBpst"
upstream_id
"resp_038e288dd2e32491016a4fe62303848197be7279550d5da881"
total_cost
0.00513
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
60.28%
Matches word count
n/a
neededClean
false
words
215
43.76%
Dialogue to Total Word Ratio
Ratio: 59.53%, Deviation: 9.53%
neededClean
false
wordsTotal
215
wordsDialogue
128
52.0157%