NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-09-01KX416QCF5397AZJH05M7381R
Run Details
Model:
GPT-5.6 Sol (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
17.9s
Cost:
$0.039990
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.68%
Dialogue to Total Word Ratio
(details)
99.8408%
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 blueprints across a café table, pinning one corner with a custard tart and another with Bill’s elbow. The blueprint was actually a crayon drawing of Happy Hippo Playbarn, obtained from a six-year-old informant for three jelly beans and diplomatic immunity from bedtime. “Clown entrance, cake distraction, then presents,” Molly whispered. Bill studied the drawing, upside down and with grave professional concern. “Fine, but I refuse to wear trousers that squeak again in public before lunch.” Their target was a glittering mountain of parcels belonging to twins whose father owned seventeen mattress shops and, according to Molly, had too many yachts. Molly had already secured two disguises: Princess Parsnip and Captain Cabbage, characters nobody recognized because she had invented them that morning. At three, they entered the playbarn behind a magician producing a rabbit from his sleeve. Unfortunately, the rabbit preferred Bill’s cabbage cape and pursued him through the balloon arch. Children cheered. Parents applauded what they assumed was premium entertainment. Molly reached the gift table, raised her empty sack, and froze. Every parcel bore a label: “Books for the Children’s Hospital.” She lowered the sack. Bill arrived, dragging rabbit, cape, and dignity. Together they stole only cake.
created_at
"2026-07-09T18:10:56.536Z"
7/9/2026, 6:10:56 PM
model
"openai/gpt-5.6-sol-20260709"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
15969
moderation_latency
(null)
generation_time
17576
tokens_prompt
77
tokens_completion
471
native_tokens_prompt
66
native_tokens_completion
1322
native_tokens_completion_images
0
native_tokens_reasoning
1054
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
0.03999
router
(null)
provider_responses
0
endpoint_id
"a54c5de0-89bf-4ad7-a212-cf977eed918a"
id
"resp_00038597702b86c9016a4fe4309dd88190a40d8ac6a96ba25b"
is_byok
false
latency
271
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-1783620656-pjDS6OK6olp2aHo3YVNj"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1783620656-xCK5HCCLlGOykfEehHzT"
upstream_id
"resp_00038597702b86c9016a4fe4309dd88190a40d8ac6a96ba25b"
total_cost
0.03999
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
100.00%
Matches word count
n/a
neededClean
false
words
200
99.68%
Dialogue to Total Word Ratio
Ratio: 12.38%, Deviation: 2.38%
neededClean
false
wordsTotal
202
wordsDialogue
25
99.8408%