NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0MVVXVDT6NB7ESN3CBABX6
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
24.4s
Cost:
$0.043620
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
99.9995%
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 crouched behind the hedge opposite number seventeen, wearing a black catsuit, a paper crown, and the guilty expression of a substitute magician. Through the window, balloons bobbed like tiny informants above a mountain of glittering parcels. Bill unfolded their blueprint, which was actually a menu from Pizza Palace with arrows drawn in ketchup. "Molly, we grab the presents, dodge the clown, and exit through the bouncy castle." "Bill, honestly, that's a jelly mold." They studied the garden. The bouncy castle wheezed majestically beside a trestle table stacked with cupcakes, while six sugar-powered children orbited it at unsafe velocity. Molly checked her toolkit: lock picks, sack, party blower, emergency sherbet. Bill produced disguises: two cardboard dinosaur heads and one badge reading Official Uncle. The plan depended on timing. At precisely three, the entertainer would ask for volunteers, parents would applaud with exhausted hope, and the dog would chase anyone smelling of sausage rolls. Molly had eaten three. Bill nodded gravely and put on the triceratops head backward. Molly sighed, adjusted his horns, and whispered that no jury would convict them if the wrapping paper was this tasteful. Then the door opened, and a toddler offered them cake without blinking.
created_at
"2026-04-24T21:03:23.59Z"
4/24/2026, 9:03:23 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
23006
moderation_latency
(null)
generation_time
24238
tokens_prompt
77
tokens_completion
433
native_tokens_prompt
66
native_tokens_completion
1443
native_tokens_completion_images
0
native_tokens_reasoning
1178
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
0.04362
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0bb104cc6eb620cf0169ebda9bbd7c8196b8a9c5263f6f6882"
is_byok
false
latency
377
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-1777064603-kNfVBG0QBId6Rw5gHErV"
session_id
(null)
api_type
"completions"
id
"gen-1777064603-D2b1fn80ZgDOWG7nBsdg"
upstream_id
"resp_0bb104cc6eb620cf0169ebda9bbd7c8196b8a9c5263f6f6882"
total_cost
0.04362
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
199
100.00%
Dialogue to Total Word Ratio
Ratio: 10.00%, Deviation: 0.00%
neededClean
false
wordsTotal
200
wordsDialogue
20
99.9995%