NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX41G2AFFBTPYSS0R3RX7XEQ
Run Details
Model:
GPT-5.6 Sol
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.9s
Cost:
$0.008940
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
90.6354%
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 spread the crayon map across the dashboard, weighting its corners with liquorice coins. Beyond the windscreen, balloons bobbed above the community hall like brightly coloured surveillance drones. “The clown leaves at three,” Molly said. “We enter disguised as magicians.” Bill adjusted his purple cape. It shed glitter whenever he breathed, turning the van into a hazardous snow globe. “Do you know magic?” “I can vanish quickly.” They watched parents unload towers of presents: robots, dolls, board games, and one suspiciously bicycle-shaped package wrapped in dinosaurs. Molly’s eyes shone with professional greed. Bill’s stomach rumbled with professional hunger. Their plan had six stages. Stage one involved mingling. Stage two required cake. Stages three through six were simply labelled IMPROVISE in increasingly frantic handwriting. At precisely two fifty-eight, they approached the hall. Molly carried an empty trunk; Bill carried a wand fashioned from a stolen aerial. A small girl blocked the entrance, wearing a cardboard badge marked SECURITY. “Password?” she demanded. Molly froze. Bill consulted the map, though it contained only a drawing of a dragon eating a policeman. “Birthday?” he guessed. The girl narrowed her eyes, then stamped their hands. Inside, thirty children turned expectantly. The real magician had cancelled. Molly smiled weakly. Bill climbed into the trunk. It locked. Everyone applauded.
created_at
"2026-07-09T18:16:02.79Z"
7/9/2026, 6:16:02 PM
model
"openai/gpt-5.6-sol-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
994
moderation_latency
(null)
generation_time
8604
tokens_prompt
77
tokens_completion
390
native_tokens_prompt
66
native_tokens_completion
287
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
0.00894
router
(null)
provider_responses
0
endpoint_id
"a54c5de0-89bf-4ad7-a212-cf977eed918a"
id
"resp_064440da604ad137016a4fe562f808819092bb2c766469f77f"
is_byok
false
latency
227
model_permaslug
"openai/gpt-5.6-sol-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-1783620962-4ZfWKTJsVc1vgjhUxRCU"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620962-T0lyGNvmopbLrR5jO34W"
upstream_id
"resp_064440da604ad137016a4fe562f808819092bb2c766469f77f"
total_cost
0.00894
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
81.27%
Matches word count
n/a
neededClean
false
words
212
100.00%
Dialogue to Total Word Ratio
Ratio: 9.35%, Deviation: 0.65%
neededClean
false
wordsTotal
214
wordsDialogue
20
90.6354%