NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PR6H3GY2BPYJNYAQ2FG7F
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
21.9s
Cost:
$0.036240
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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
Outside the community hall, Molly crouched behind a hedge trimmed into the shape of a disappointed duck. Bill unfolded a crayon map he had stolen from a refrigerator, upside down and sticky with jam. Inside, thirty children shrieked around a magician whose rabbit looked unionized. The gift table glittered beneath bows, ribbons, and one suspiciously large package labeled Educational. Molly sniffed the air like a jewel appraiser at a bakery. “Clown suit?” Molly asked. “Too subtle,” Bill said. “We need balloons, cake crumbs, and the moral flexibility of raccoons. Also tiny hats. Lots. Obviously.” Molly nodded gravely, then produced two party blowers and a clipboard titled Operation Birthday Regret. Bill admired it until the blower in his pocket unfurled with a treasonous squeak. A toddler at the window pressed frosting to the glass and stared directly at them. They froze. The toddler waved a gummy fist, either greeting them or summoning security. Molly waved back with professional menace, which looked like jazz hands. Bill swallowed. Their grand larceny suddenly depended on whether a three-year-old accepted bribes in stickers. Somewhere inside, everyone began singing, and the presents seemed to sparkle with frosting-coated innocence and terrible weight. Molly reconsidered her career path.
created_at
"2026-04-24T21:36:20.528Z"
4/24/2026, 9:36:20 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
19828
moderation_latency
(null)
generation_time
21594
tokens_prompt
77
tokens_completion
455
native_tokens_prompt
66
native_tokens_completion
1197
native_tokens_completion_images
0
native_tokens_reasoning
924
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
0.03624
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_030d8f4cab113fff0169ebe254a57c8195b1ce7f297c171635"
is_byok
false
latency
360
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-1777066580-sfEUyMMJ1IqSIVtjlcx2"
session_id
(null)
api_type
"completions"
id
"gen-1777066580-89m3rXA1pri6rSOm0e5A"
upstream_id
"resp_030d8f4cab113fff0169ebe254a57c8195b1ce7f297c171635"
total_cost
0.03624
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
200
100.00%
Dialogue to Total Word Ratio
Ratio: 9.85%, Deviation: 0.15%
neededClean
false
wordsTotal
203
wordsDialogue
20
100.0000%