NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX40KAP27CQSYATK7R1H5V4X
Run Details
Model:
GPT-5.6 Luna (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
13.2s
Cost:
$0.014244
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
3.62%
Matches word count
(details)
99.99%
Dialogue to Total Word Ratio
(details)
51.8051%
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
Rain polished the cobblestones outside the community hall, turning every streetlamp into a trembling gold coin. Molly crouched behind a hedge, wearing a borrowed magician’s cape and the expression of someone who had never successfully pulled anything from a hat. Bill lay beside her in a tuxedo two sizes too small, his fake mustache drooping like a wet caterpillar. He clutched a sack labeled EMERGENCY BALLOONS, which contained only rope, biscuits, and an alarming number of rubber ducks. Molly whispered, “Presents wait beneath clown mural; enter disguised as entertainers.” Bill replied, “I hate children’s parties, but I hate affordable security even more.” The hall throbbed with music, shrieks, and the unmistakable percussion of a parent losing an argument with a balloon. Through the windows, they saw children circling a table piled with brightly wrapped boxes. A cardboard dragon guarded the entrance, its painted eyes accusing every adult who approached. Molly produced two juggling balls from her pocket. Bill produced one and immediately dropped it down his trousers. The ball rolled beneath the hedge, where a terrier seized it and fled. Bill followed, crawling with the dignity of a diplomat escaping an opera. Molly watched dog vanish, then adjusted cape. A volunteer mistook them for entertainers and opened the door. They swept inside, stuffing every present into the sack while Bill distracted everyone with juggling.
created_at
"2026-07-09T18:00:20.939Z"
7/9/2026, 6:00:20 PM
model
"openai/gpt-5.6-luna-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
12117
moderation_latency
(null)
generation_time
12553
tokens_prompt
77
tokens_completion
375
native_tokens_prompt
66
native_tokens_completion
2363
native_tokens_completion_images
0
native_tokens_reasoning
2070
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
0.014244
router
(null)
provider_responses
0
endpoint_id
"eebea444-34a5-4642-a766-cb319471d33a"
id
"resp_0d3c760742b0da74016a4fe1b5119481959a304a8e613f4ba6"
is_byok
false
latency
217
model_permaslug
"openai/gpt-5.6-luna-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-1783620020-gWC1iqpUyD1prKlt4mH9"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620020-6G7sUIzb9jo2tQOKaXPx"
upstream_id
"resp_0d3c760742b0da74016a4fe1b5119481959a304a8e613f4ba6"
total_cost
0.014244
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
3.62%
Matches word count
n/a
neededClean
false
words
224
99.99%
Dialogue to Total Word Ratio
Ratio: 8.93%, Deviation: 1.07%
neededClean
false
wordsTotal
224
wordsDialogue
20
51.8051%