NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HP7HDZW8BEBZRKPKRSG5E
Run Details
Model:
GPT-6 Sol
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.0s
Cost:
$0.003202
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
1.01%
Dialogue to Total Word Ratio
(details)
49.8634%
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 studied the invitation. “Rainbow Castle, three o’clock. Twenty children, twelve adults, one inflatable dragon.” Bill adjusted his burglar mask. “That dragon looks intimidating.” “It’s made of vinyl.” “So are most raincoats. Still hate thunder.” “We enter as entertainers,” Molly said. “You juggle, I collect the presents.” “I can’t juggle.” “You can drop things theatrically.” “What if a parent asks questions?” “Tell them you’re Bill the Magnificent.” “Could I be Bill the Adequate? Lower expectations.” “Fine. Once everyone’s watching you, I’ll carry the gifts to our van.” “We have a van?” “We have your bicycle trailer.” “It says BILL’S BREAD DELIVERIES.” “Then wear your bakery apron.” Bill frowned. “Molly, these presents are for children.” “Exactly. Children have terrible security.” “No, I mean stealing them feels wrong.” “You brought that up rather late.” “I was distracted by the dragon.” A scream rose from inside. A child burst through the gate, followed by six others and a woman holding a deflated balloon. “Are you the entertainers?” she asked. Molly froze. Bill stepped forward. “Yes. I’m Bill the Adequate. My assistant performs disappearing acts.” The woman sighed. “Wonderful. Can she make twenty-seven sticky children disappear?” Molly glanced at Bill. “Change of plan?” “Absolutely,” Bill whispered. “We steal the cake.”
created_at
"2026-09-23T16:30:56.053Z"
9/23/2026, 4:30:56 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3787
moderation_latency
(null)
generation_time
8935
tokens_prompt
75
tokens_completion
403
native_tokens_prompt
66
native_tokens_completion
307
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
0.003202
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790181056-IfwkELx4lgBzmqaNGvIL"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790181056-VDejdsqtPQWb9okFgYtE"
upstream_id
"resp_0548d827446462e1016ab3fec04d1c87d1bc7a5cf9d702f251"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_0548d827446462e1016ab3fec04d1c87d1bc7a5cf9d702f251"
is_byok
false
latency
1910
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.003202
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
98.71%
Matches word count
n/a
neededClean
false
words
206
1.01%
Dialogue to Total Word Ratio
Ratio: 75.36%, Deviation: 14.64%
neededClean
false
wordsTotal
207
wordsDialogue
156
49.8634%