NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37J2NQEFT0A71JV2QEED5ND
Run Details
Model:
GPT-6 Sol
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.0s
Cost:
$0.003132
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
28.4888%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 a crayon map across the café table. The birthday party occupied a community hall shaped, according to her drawing, like a suspicious potato. Bill studied the paper while a balloon bobbed against the ceiling above them. “The presents are by the cake,” Molly said. “We slip in during the magician’s act.” “How?” “Through the front door. We’re dressed as guests.” Bill looked down at his pirate costume. “I’m dressed as a pirate.” “Children love pirates.” “Do they love pirates carrying empty sacks?” “Tell them they’re for treasure.” Bill tapped the map. “What’s the squiggle beside the cake?” “An adult making balloon animals.” “That squiggle has a whistle.” “A precaution.” “Against what?” “Pirates, apparently.” At noon, they reached the hall. Molly wore a paper crown; Bill carried two sacks. Through the window, they saw a mountain of bright packages, a magician pulling ribbons from his sleeve, and twelve children chanting for cake. Molly reached for the door. “Wait,” Bill said. “What if they ask whose parents we are?” “Say we’re here for the magician.” “He hired pirates?” Before Molly could answer, the door opened. A child pointed at Bill. “Finally! The pirate for musical chairs!” The children seized his hands. Molly stayed near the presents until the music stopped. Bill won, accidentally. His prize was a bag of sweets.
created_at
"2026-09-23T16:37:43.799Z"
9/23/2026, 4:37:43 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2744
moderation_latency
(null)
generation_time
9950
tokens_prompt
75
tokens_completion
386
native_tokens_prompt
66
native_tokens_completion
300
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
0.003132
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790181463-jxT12odE4wtWkABbM6Nq"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790181463-YpPNB3wwyBy58Oxj20VP"
upstream_id
"resp_0c2cb719f0fb4728016ab40057e5b487d1b7245aa7e07fcf70"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_0c2cb719f0fb4728016ab40057e5b487d1b7245aa7e07fcf70"
is_byok
false
latency
718
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.003132
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
20.19%
Matches word count
n/a
neededClean
false
words
220
36.79%
Dialogue to Total Word Ratio
Ratio: 40.00%, Deviation: 10.00%
neededClean
false
wordsTotal
220
wordsDialogue
88
28.4888%