NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX40YSHHDFCMN1BTFH5HQ294
Run Details
Model:
GPT-5.6 Terra
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
5.3s
Cost:
$0.004815
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
52.4451%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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, why are we whispering? It’s a bouncy castle, not Fort Knox.” “Because, Bill, children have ears like bats and grudges like tax inspectors.” “We’re stealing presents, not national secrets.” “Same principle. Look at the loot list: robot dinosaur, glitter microscope, seventeen identical unicorn purses.” “Who gives seventeen unicorn purses?” “Grandparents who panic in shopping centres.” “So what’s the plan?” “You go in dressed as a magician.” “I don’t know magic.” “You know how to make a wallet disappear.” “Only mine. Usually into a pub.” “I’ll be the assistant.” “In sequins?” “In authority. I’ll announce a surprise party trick.” “And then?” “You distract them with a card trick.” “I have cards.” “You have parking tickets.” “They’re rectangular.” “Fine. While you explain the mystery of the disappearing Ford Fiesta, I load the gifts into the cake trolley.” “The cake trolley has a cake on it.” “Not after I replace it with cushions.” “Children will notice their cake is cushions.” “Only if they’re hungry.” “Children are always hungry.” “Then we improvise.” “With what?” “You eat a cushion.” “I’m not eating a cushion.” “Bill, commitment is why you’re still a petty thief.” “I prefer ‘small-business criminal.’” “Put on the cape.” “It has stars.” “Good. Children trust stars.” “Children also trust clowns.” “Exactly why we’re not bringing Gary.”
created_at
"2026-07-09T18:06:36.601Z"
7/9/2026, 6:06:36 PM
model
"openai/gpt-5.6-terra-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
581
moderation_latency
(null)
generation_time
5150
tokens_prompt
77
tokens_completion
465
native_tokens_prompt
66
native_tokens_completion
310
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
0.004815
router
(null)
provider_responses
0
endpoint_id
"3cc89000-ae34-4dde-9c7d-5ce009c8af0b"
id
"resp_0fd6cf7b8f44b06b016a4fe32cb1a88190810bec1b6de92467"
is_byok
false
latency
221
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-1783620396-XTK40FcKPgdkEr4mFL4c"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620396-TiGe738Rz2uEuU2QRFKU"
upstream_id
"resp_0fd6cf7b8f44b06b016a4fe32cb1a88190810bec1b6de92467"
total_cost
0.004815
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
68.10%
Matches word count
n/a
neededClean
false
words
214
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
214
wordsDialogue
214
52.4451%