NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HCBSCVP7FZJB242B3Z2PX
Run Details
Model:
GPT-6 Sol
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.5s
Cost:
$0.003012
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
92.48%
Dialogue to Total Word Ratio
(details)
94.2314%
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 studied the invitation beneath the bakery awning. “Three o’clock. Princess costumes encouraged.” Bill adjusted his cardboard crown. “I still think dressing as a magician would explain the empty boxes.” “You said you couldn’t do tricks.” “I can make a sandwich disappear.” Rain stippled the invitation. The birthday girl’s smiling photograph made Molly feel like a villain, which, professionally speaking, she was. “We grab the presents during the puppet show,” Molly said. “And if someone asks?” “We say we’re taking them to be wrapped.” Bill considered this. “They’re already wrapped.” “Then we’re taking them to be unwrapped.” Inside the hall, children shrieked with birthday excitement. Bill pressed his crown down while Molly surveyed a mountain of glittering packages. “Those are enormous,” he whispered. “So?” “My sack fits maybe two.” “Then take the small ones.” “What if the small ones contain socks?” A little girl appeared beside them, holding a wand. “Are you the surprise guests?” Molly and Bill exchanged a look. “Absolutely,” Molly said. “Good,” the girl replied. “We need someone to carry the presents to the hospital party next door.” Bill lifted the nearest box. “We’re volunteers now?” Molly picked up three more. “Apparently.” “And after that?” “We steal some cake.” “Finally,” Bill said, “a sensible plan.”
created_at
"2026-09-23T16:25:32.724Z"
9/23/2026, 4:25:32 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2423
moderation_latency
(null)
generation_time
7439
tokens_prompt
75
tokens_completion
393
native_tokens_prompt
66
native_tokens_completion
288
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
0.003012
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790180732-kRdXUoAdWGsJpDZ1kaec"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790180732-VVg95aawHO32A3RK043k"
upstream_id
"resp_096c1cb7e7135bd0016ab3fd7cd46487d18f8ab78640a82251"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_096c1cb7e7135bd0016ab3fd7cd46487d18f8ab78640a82251"
is_byok
false
latency
734
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.003012
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
95.99%
Matches word count
n/a
neededClean
false
words
208
92.48%
Dialogue to Total Word Ratio
Ratio: 55.29%, Deviation: 5.29%
neededClean
false
wordsTotal
208
wordsDialogue
115
94.2314%