NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HCE1NQX7DMDXTYEVF6QK8
Run Details
Model:
GPT-6 Sol
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
6.4s
Cost:
$0.003292
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
51.93%
Matches word count
(details)
31.46%
Dialogue to Total Word Ratio
(details)
41.6907%
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 flattened the invitation against the café table. “Saturday, two o’clock. Presents in the living room.” Bill leaned over it. “You got an invitation?” “The birthday girl handed one to every customer at the bakery. I bought a bun.” “Expensive reconnaissance.” “It had icing. Now, we go in with the other parents, wait for cake, then carry the presents out through the kitchen.” “All of them?” “That’s what the client paid for.” “What client hires us to rob a children’s party?” “One who insisted on anonymity.” Bill studied the invitation. “Molly, why does it say ‘No gifts, please’?” “People always bring them anyway.” “And why is the birthday girl turning forty?” “Because you’re holding it upside down.” “I’m not. Look. ‘Fortieth birthday party for Mr. Pickles.’” Molly snatched the card. “Mr. Pickles is the dog. The child is four.” “Then why does it say ‘Please bring a present for the shelter’?” They looked at each other. “We’re stealing donations,” Bill said. Molly reached for her phone. “I’m calling the client.” “Put it on speaker.” A man answered. “Did you get the invitation?” “Who are you?” Molly asked. “Mr. Pickles’s owner. The shelter refused my old sofa. I want revenge.” Bill pushed back his chair. “We’re not doing it.” “Fine,” said Molly. “But I’m keeping the bun.”
created_at
"2026-09-23T16:25:35.036Z"
9/23/2026, 4:25:35 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
814
moderation_latency
(null)
generation_time
6388
tokens_prompt
75
tokens_completion
391
native_tokens_prompt
66
native_tokens_completion
316
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
0.003292
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790180735-cFXYzuxe7JBuv7HRdL7O"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790180735-9MbsBnYUsPGAweVkNqVu"
upstream_id
"resp_02b721f8e73a7679016ab3fd7f223087d1a9158bab32f01ba9"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_02b721f8e73a7679016ab3fd7f223087d1a9158bab32f01ba9"
is_byok
false
latency
484
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.003292
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
51.93%
Matches word count
n/a
neededClean
false
words
216
31.46%
Dialogue to Total Word Ratio
Ratio: 79.63%, Deviation: 10.37%
neededClean
false
wordsTotal
216
wordsDialogue
172
41.6907%