NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PND8DE3VYVRD76YJPZB44
Run Details
Model:
GPT-5.5
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.1s
Cost:
$0.008760
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9994%
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 crayon-drawn map across the bonnet of their van, which was disguised, unconvincingly, as a mobile library. The target sat across the street: a garden full of balloons, bunting, sugared children, and a mountain of presents stacked beside a bouncy castle shaped like a dragon with indigestion. Bill adjusted his fake clown nose and squinted through binoculars. “We nab gifts, not cake, understood?” Molly tapped the map with a liquorice stick. “Focus. Enter as entertainers.” Behind them, the van coughed out a puff of glitter from the exhaust. Neither mentioned it. Last week’s robbery of the craft shop still clung to everything. The birthday boy’s father emerged carrying juice boxes like a nervous waiter in a tiny war. Bill frowned. “What if they ask us juggling?” “Then juggle,” Molly said. “With what?” Molly opened a sack. Inside were rubber chickens, three plungers, and a framed photo of Bill’s mother. Bill sighed. Their plan was simple: perform terrible magic, herd the children toward the bouncy castle, wheel the presents into the van, and vanish before anyone noticed the library had no books. Across the street, a child pointed. “Clowns!” Molly grinned. The dragon deflated loudly, like fate changing its mind.
created_at
"2026-04-24T21:34:49.11Z"
4/24/2026, 9:34:49 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
520
moderation_latency
(null)
generation_time
7953
tokens_prompt
77
tokens_completion
343
native_tokens_prompt
66
native_tokens_completion
281
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"
usage
0.00876
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0e746474b89f4c4b0169ebe1f933008190806518f1975f876e"
is_byok
false
latency
243
model_permaslug
"openai/gpt-5.5-20260423"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777066489-bjaiZQQn2rrfo0BkQttt"
session_id
(null)
api_type
"completions"
id
"gen-1777066489-Nf9RtFmqPWdcr69OhVPn"
upstream_id
"resp_0e746474b89f4c4b0169ebe1f933008190806518f1975f876e"
total_cost
0.00876
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
201
100.00%
Dialogue to Total Word Ratio
Ratio: 10.40%, Deviation: 0.40%
neededClean
false
wordsTotal
202
wordsDialogue
21
99.9994%