NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX4139HB4KJDB7YDRV3ZNXA2
Run Details
Model:
GPT-5.6 Sol
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.7s
Cost:
$0.008790
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
93.83%
Dialogue to Total Word Ratio
(details)
87.5515%
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 spread the birthday invitation across the café table, pinning its corners with sugar packets. Purple unicorns galloped around the address, beneath instructions to wear sparkles and bring enthusiasm. Bill regarded it as though enthusiasm were a controlled substance. “We enter disguised as magicians,” Molly said. “Nobody questions magicians near cake.” “I hate rabbits,” Bill muttered. “They know what I did.” At three o’clock, the community hall would contain twenty children, thirty presents, two exhausted parents, and one entertainer named Magnifico Pete. Molly had already redirected Pete to a retirement luncheon across town, where his disappearing handkerchiefs would probably cause panic. Bill studied the floor plan. The gift table stood beside the emergency exit, guarded by a grandmother with orthopedic shoes and the suspicious instincts of a prison warden. “Grandmother is the problem,” he whispered. “Compliment her cardigan. Then faint.” “Why me?” “You collapse beautifully.” Their escape vehicle, a stolen ice-cream van, waited outside with its cheerful melody permanently jammed on. Molly planned to load the presents during musical chairs, when confusion reached operational levels. Bill would create a diversion by producing a sausage dog from a top hat. Neither thief had considered the dog’s opinion. Under the table, it quietly ate the invitation, then Molly’s map, and finally Bill’s false moustache.
created_at
"2026-07-09T18:09:04.05Z"
7/9/2026, 6:09:04 PM
model
"openai/gpt-5.6-sol-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
661
moderation_latency
(null)
generation_time
8163
tokens_prompt
77
tokens_completion
391
native_tokens_prompt
66
native_tokens_completion
282
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
0.00879
router
(null)
provider_responses
0
endpoint_id
"a54c5de0-89bf-4ad7-a212-cf977eed918a"
id
"resp_0233417bbeaf5e20016a4fe3c01c1c819082485076cdaaf02b"
is_byok
false
latency
198
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-1783620544-94Qeus90t1ux7VXtiRup"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620544-1SsIdIU8nPKTR5GjR2gX"
upstream_id
"resp_0233417bbeaf5e20016a4fe3c01c1c819082485076cdaaf02b"
total_cost
0.00879
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
81.27%
Matches word count
n/a
neededClean
false
words
212
93.83%
Dialogue to Total Word Ratio
Ratio: 15.02%, Deviation: 5.02%
neededClean
false
wordsTotal
213
wordsDialogue
32
87.5515%