NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37HMT9RK9WF1X7Y76FQPJP5
Run Details
Model:
GPT-6 Sol (Reasoning, Medium)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
19.1s
Cost:
$0.012142
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
97.9933%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 a streetlamp, its glitter migrating onto her gloves like evidence with excellent public relations. Across the road, a birthday banner sagged over the community hall, where thirty children were apparently celebrating one small person's continued existence with an alarming quantity of wrapped merchandise. “We enter disguised as magicians,” Molly said. “I refuse to swallow swords,” Bill said. Bill peered through the window. A clown inflated a sausage balloon, lost control, and accidentally knighted a grandmother. Near the cake stood a mountain of presents, defended by paper hats and the unshakeable confidence of people who had never met Bill. “Then carry the glitter cannon,” Molly said. “Does it fire actual glitter?” Bill asked. Molly unfolded their blueprint, which was a napkin bearing two arrows, a stain, and the words PRESENTS THIS WAY. Bill recognized the stain from lunch and immediately questioned their operational budget. They would enter through the side door, mingle until the candles went out, then roll the gift table toward the waiting van. Unfortunately, the van belonged to Bill's mother, who had insisted he return it before dinner and absolutely not transport any more garden furniture. Inside, someone struck up a birthday song. Molly checked her watch. Bill checked for swords.
created_at
"2026-09-23T16:30:09.738Z"
9/23/2026, 4:30:09 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
17192
moderation_latency
(null)
generation_time
19073
tokens_prompt
75
tokens_completion
475
native_tokens_prompt
66
native_tokens_completion
1201
native_tokens_completion_images
0
native_tokens_reasoning
939
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
0.012142
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790181009-MI7DRBGfeeNtDPjEIfbq"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790181009-jwU2pIY1hHR4SjoeccNz"
upstream_id
"resp_03c8d17fd4e799ba016ab3fe91dc9887d18af0eef2ba9edbee"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_03c8d17fd4e799ba016ab3fe91dc9887d18af0eef2ba9edbee"
is_byok
false
latency
958
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.012142
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
100.00%
Dialogue to Total Word Ratio
Ratio: 9.62%, Deviation: 0.38%
neededClean
false
wordsTotal
208
wordsDialogue
20
97.9933%