NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37J09YHM2G7MGQY29KEA839
Run Details
Model:
GPT-6 Sol (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
23.1s
Cost:
$0.015272
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
66.39%
Dialogue to Total Word Ratio
(details)
83.1958%
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 said, “We sneak in disguised as balloon artists. Nobody questions balloon artists, especially when they look disappointed in their career choices.” Bill said, “I can make a balloon snake.” “That’s just an inflated balloon.” “Exactly. Minimal effort, maximum reptile.” “We locate the present table, fill our sack, and leave before cake.” “One problem: the invitation says everyone must bring a present.” “We’ll bring a present.” “What present?” “The sack. It’s wrapped in optimism.” “Another problem: the birthday child is my niece.” “You have a niece?” “Yes. She can identify me by my ears. They’re ambitious.” “Then wear a hat.” “She gave me every hat I own.” “Fine. I’ll distract her with a balloon giraffe.” “You can’t make a giraffe.” “I’ll tell her it’s a snake with excellent posture.” “What if the parents recognize us from last year?” “Last year, we were clowns. This year, we’re professionals.” “We stole the cake last year.” “We borrowed it. Temporarily. In our stomachs.” “Bill, are we really stealing presents from children?” “Of course not. We’re stealing them from a table.” “That distinction feels flimsy.” “Fine. New plan: we give the kids balloons and steal the leftover cupcakes.” “We’re terrible thieves.” “We’re outstanding guests.”
created_at
"2026-09-23T16:36:26.2Z"
9/23/2026, 4:36:26 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
20775
moderation_latency
(null)
generation_time
23054
tokens_prompt
75
tokens_completion
384
native_tokens_prompt
66
native_tokens_completion
1514
native_tokens_completion_images
0
native_tokens_reasoning
1228
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
0.015272
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790181386-gi3lKNLlEpriF0EQuWEN"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790181386-I4Pt3UWfTlUQJQYJ77Zp"
upstream_id
"resp_0371567d564271e6016ab4000a4cc887d193be1da18ea5a7dd"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_0371567d564271e6016ab4000a4cc887d193be1da18ea5a7dd"
is_byok
false
latency
745
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.015272
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
100.00%
Matches word count
n/a
neededClean
false
words
200
66.39%
Dialogue to Total Word Ratio
Ratio: 98.00%, Deviation: 8.00%
neededClean
false
wordsTotal
200
wordsDialogue
196
83.1958%