NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX415VKCP985H2J89EKWFXC2
Run Details
Model:
GPT-5.6 Sol
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.4s
Cost:
$0.008880
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
93.1902%
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 birthday invitation across the dashboard, smoothing glitter beneath her gloves. A cartoon dinosaur grinned up at them, ignorant of crime. “We enter disguised as entertainers,” Molly said. “You juggle. I make balloons.” “I can’t juggle,” Bill whispered. “Or make balloons.” “That’s why I make balloons.” Outside, children swarmed the community hall, shrieking with the savage delight of tiny aristocrats. Parents carried towers of wrapped presents through the doors. Bill watched a bicycle disappear inside and sighed greedily. Their van contained two clown suits, three empty sacks, a smoke machine, and a cake Molly had baked as camouflage. The icing read HAPPY BIRTDAY, because Bill had eaten the spare H. Molly outlined the operation. They would trigger the smoke machine near the puppet theater, announce a dragon emergency, evacuate everyone, then wheel the gifts out inside a papier-mâché castle. Simple, elegant, almost educational. Bill nodded, then opened the cake box. The cake was gone. On the floor sat a guilty terrier wearing frosting like war paint. Before Molly could object, the hall doors burst open. Twenty children spotted the clown suits hanging in the van. The mob charged. Molly locked the doors. Bill started the engine. Behind them, the terrier barked, and the smoke machine began billowing purple clouds.
created_at
"2026-07-09T18:10:28.085Z"
7/9/2026, 6:10:28 PM
model
"openai/gpt-5.6-sol-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
710
moderation_latency
(null)
generation_time
8236
tokens_prompt
77
tokens_completion
365
native_tokens_prompt
66
native_tokens_completion
285
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
0.00888
router
(null)
provider_responses
0
endpoint_id
"a54c5de0-89bf-4ad7-a212-cf977eed918a"
id
"resp_043797b2aa91b1cd016a4fe414306881948cb1f6bbfabbe2ae"
is_byok
false
latency
293
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-1783620628-wq7ixqxXLpDw3x374iTG"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620628-RciFy9lC0T5NSmn1XBh1"
upstream_id
"resp_043797b2aa91b1cd016a4fe414306881948cb1f6bbfabbe2ae"
total_cost
0.00888
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
86.38%
Matches word count
n/a
neededClean
false
words
211
100.00%
Dialogue to Total Word Ratio
Ratio: 9.91%, Deviation: 0.09%
neededClean
false
wordsTotal
212
wordsDialogue
21
93.1902%