NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX41B8SPJHPMVNB6C8K9D5ZV
Run Details
Model:
GPT-5.6 Sol
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.2s
Cost:
$0.009390
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
63.5818%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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 a crayon map across the van’s dashboard. Through the rain, balloons bobbed above the community hall like brightly colored witnesses. Bill adjusted his borrowed clown wig and frowned. “That’s your disguise? You look like broccoli after an electrical accident.” “Says the woman wearing a princess crown over a ski mask.” “It’s called elegance. Now, the presents are beside the cake.” “And the children?” “Distracted by the magician at two thirty.” “What if he’s good?” “No magician performing beside a radiator is good.” Bill studied the map upside down. “We enter through the kitchen, crawl under the buffet, grab everything, and escape through the bouncy castle.” “The bouncy castle isn’t an exit.” “Not with that attitude.” A burst of cheering rattled the hall windows. Molly checked her watch. Across the car park, a tiny pirate pointed directly at them. “We’ve been spotted,” Bill whispered. “He’s six.” “Six-year-olds talk.” The pirate marched closer, trailed by twenty children. Molly started the engine, but the van coughed and died. “Plan B?” Bill asked. Molly stared at the advancing horde. “We give them your balloon animals.” “I can only make snakes.” “Then today’s party has a reptile theme.” The doors opened. Children swarmed them, demanding swords, dogs, and giraffes. Ten minutes later, Molly and Bill escaped carrying nothing but cake and shame.
created_at
"2026-07-09T18:13:25.438Z"
7/9/2026, 6:13:25 PM
model
"openai/gpt-5.6-sol-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
626
moderation_latency
(null)
generation_time
10057
tokens_prompt
77
tokens_completion
410
native_tokens_prompt
66
native_tokens_completion
302
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
0.00939
router
(null)
provider_responses
0
endpoint_id
"a54c5de0-89bf-4ad7-a212-cf977eed918a"
id
"resp_0b48fbebb3cebeaf016a4fe4c5847c81969efd9575d7f10350"
is_byok
false
latency
261
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-1783620805-csyEgHg1GWpOusvBw2Bl"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620805-I0omwycdv3DFZjcnxKOk"
upstream_id
"resp_0b48fbebb3cebeaf016a4fe4c5847c81969efd9575d7f10350"
total_cost
0.00939
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
27.17%
Matches word count
n/a
neededClean
false
words
219
100.00%
Dialogue to Total Word Ratio
Ratio: 49.32%, Deviation: 0.68%
neededClean
false
wordsTotal
219
wordsDialogue
108
63.5818%