NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HKX3Y7P25EF87SMGJ47X7
Run Details
Model:
GPT-6 Sol
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.1s
Cost:
$0.003342
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
11.14%
Dialogue to Total Word Ratio
(details)
19.1507%
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
“The party starts at two,” Molly said. “We go in at two-fifteen.” “Disguised as what?” Bill asked. “A responsible adult? I haven’t got the cheekbones.” “You’re the magician.” “I can’t do magic.” “You made my rent money disappear.” “That was accounting.” “You’ll perform one trick: pull a rabbit from a hat.” “Do we have a rabbit?” “We have a hat.” Bill examined the invitation. “What’s the birthday boy’s name?” “Princess Amelia.” “I’ll remember the important part.” “The presents are stacked by the cake table. While everyone watches your act, I’ll carry them out.” “All of them?” “That’s what the client paid for.” “Who hires thieves to rob a children’s party?” “Her grandmother.” “Why?” “She bought every present and wants them back. Apparently Amelia announced she’d only invited Grandma for her wallet.” “That’s cold, even for royalty.” At two-fifteen, Bill stepped into the garden, lifted his hat, and produced a sandwich. “Amazing!” cried the children. “Thank you,” Bill said. “My next trick requires everyone to close their eyes.” Molly reached the cake table. A little girl blocked her path. “Those are mine,” Amelia said. “Your grandmother sent me.” Amelia grinned. “Good. I wrapped her car keys in the biggest one.” Bill lowered his hat. “Molly? Why are we stealing a car?” “Because,” Molly said, “the client just changed our fee.”
created_at
"2026-09-23T16:29:39.845Z"
9/23/2026, 4:29:39 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2495
moderation_latency
(null)
generation_time
8024
tokens_prompt
75
tokens_completion
412
native_tokens_prompt
66
native_tokens_completion
321
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
0.003342
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790180979-J9rs0RIym9PF05bUkKZZ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790180979-oQc8jIKLU3aci2odyWb3"
upstream_id
"resp_051d748cab9d1667016ab3fe73f47887d19004f644cb78f355"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_051d748cab9d1667016ab3fe73f47887d19004f644cb78f355"
is_byok
false
latency
597
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.003342
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
27.17%
Matches word count
n/a
neededClean
false
words
219
11.14%
Dialogue to Total Word Ratio
Ratio: 77.83%, Deviation: 12.17%
neededClean
false
wordsTotal
221
wordsDialogue
172
19.1507%