NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX40ETSSHE88SA9XHQ3FQXQM
Run Details
Model:
GPT-5.6 Sol
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.2s
Cost:
$0.010890
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
99.21%
Dialogue to Total Word Ratio
(details)
97.6002%
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
“The plan is simple, Bill. We enter disguised as entertainers.” “Clowns?” “Too conspicuous.” “Magicians?” “Too competent.” “Responsible adults?” “Now you’re being ridiculous.” Molly spread a crayon map across the dashboard. “What’s the square?” “Bouncy castle.” “And the circle?” “Cake.” “And the skull?” “Birthday girl’s grandmother.” “Armed?” “Knitting needles. Sharp eyes. Peppermint breath.” “So, heavily armed.” “Exactly. We arrive at two. You juggle. I locate the presents.” “I can’t juggle.” “You throw three oranges and apologize repeatedly.” “My signature act.” “Once I’ve bagged the loot, you release the distraction.” “The rabbit?” “The toddlers.” “How?” “Announce that someone said ‘ice cream.’” “Diabolical.” “Thank you.” “What are we stealing?” “Every present.” “Even the educational ones?” “We have standards, Bill. Especially the educational ones.” “What if they recognize us?” “Wear this dinosaur costume.” “It has no trousers.” “Dinosaurs didn’t wear trousers.” “Dinosaurs didn’t attend suburban birthdays.” “Not with that attitude.” A knock sounded on the van window. “Is that the grandmother?” “Worse.” “Police?” “Birthday girl.” The child held up an invitation. “She says we’re late.” “Smile.” “She says Mum hired us.” “For what?” “Entertainment.” Molly sighed. “Bill, start apologizing.” He grabbed the oranges. “Children, prepare to be underwhelmed.” “And the presents?” “Later.” “Why?” “The grandmother’s knitting us scarves.” “Aw.” “Crime can wait.”
created_at
"2026-07-09T17:57:53.602Z"
7/9/2026, 5:57:53 PM
model
"openai/gpt-5.6-sol-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
653
moderation_latency
(null)
generation_time
8100
tokens_prompt
77
tokens_completion
560
native_tokens_prompt
66
native_tokens_completion
352
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
0.01089
router
(null)
provider_responses
0
endpoint_id
"a54c5de0-89bf-4ad7-a212-cf977eed918a"
id
"resp_0775608f3a54748f016a4fe121ada88197a2e795eb8ee129f6"
is_byok
false
latency
236
model_permaslug
"openai/gpt-5.6-sol-20260709"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1783619873-dGBWrHaHbHatUQtCzIzU"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783619873-CLBCOX9aR1UlLhVnvUjy"
upstream_id
"resp_0775608f3a54748f016a4fe121ada88197a2e795eb8ee129f6"
total_cost
0.01089
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
208
99.21%
Dialogue to Total Word Ratio
Ratio: 87.02%, Deviation: 2.98%
neededClean
false
wordsTotal
208
wordsDialogue
181
97.6002%