NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0NTVDT22C8VA924BNZB5CZ
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
49.0s
Cost:
$0.102150
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 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 crouched behind the hedge in a glittery raccoon mask, watching balloons bob beyond the church hall windows. Bill unfolded a frosting-spotted napkin labeled MASTER PLAN, upside down. Inside, children shrieked while a magician produced a disappointed dove. “Right, Bill, we enter with dignity, locate the gift table, and leave richer by twelve stuffed unicorns.” “Fourteen, Molly. I counted during the hokey pokey while maintaining criminal mystique.” “You joined the hokey pokey?” “Only as research. Also, they had tambourines, juice boxes, and suspiciously good cheese cubes.” “You wore a paper crown.” “Every king needs cover, Molly, especially near a bouncy castle full of witnesses.” A tiny girl burst outside chasing a runaway hat. She stared, then offered Molly a cupcake with tragic seriousness. Molly accepted. Bill blinked suspiciously fast. The birthday song wobbled through the wall like a guilty conscience. “Bill, new plan.” “Excellent. Smoke bomb, grappling hook, or trained ferret with tiny boots?” “No. We sneak in, add presents, and steal cake.” “Cake isn’t theft if destiny cuts it into slices. Big slices.” They marched in carrying two wrapped bricks and smiles. Ten minutes later, Molly wore a princess sash, Bill danced with Grandma, and every present remained unstolen.
created_at
"2026-04-24T21:20:18.883Z"
4/24/2026, 9:20:18 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
47586
moderation_latency
(null)
generation_time
48837
tokens_prompt
77
tokens_completion
898
native_tokens_prompt
66
native_tokens_completion
3394
native_tokens_completion_images
0
native_tokens_reasoning
3106
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
0.10215
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_06c9fafbaa73ae850169ebde9301dc8197ab9fc4f751384327"
is_byok
false
latency
293
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-1777065618-aEzbkfhBgb40aBW9zL63"
session_id
(null)
api_type
"completions"
id
"gen-1777065618-IrF7xsmcBpfoYMQk93zp"
upstream_id
"resp_06c9fafbaa73ae850169ebde9301dc8197ab9fc4f751384327"
total_cost
0.10215
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: 49.75%, Deviation: 0.25%
neededClean
false
wordsTotal
201
wordsDialogue
100
100.0000%