NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0MTZ232P3PCAQ5ZK2H3TTH
Run Details
Model:
GPT-5.5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
8.3s
Cost:
$0.009630
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
87.55%
Dialogue to Total Word Ratio
(details)
92.5883%
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, peering at the backyard circus of balloons, cupcakes, and sugared chaos. Bill unfolded a map drawn on a napkin, upside down. “Phase one: we enter through the bouncy castle,” Molly said. “That’s not a door,” Bill whispered. “It’s a lifestyle choice.” Bill squinted. “And phase two?” “We blend in.” “You’re wearing a black turtleneck.” “So are eight of the dads.” A child shrieked with joy as a magician produced a rabbit from a hat. Bill flinched. “The rabbit saw me,” he said. “The rabbit knows nothing.” Near the picnic table, a mountain of wrapped gifts glittered beneath a banner reading HAPPY BIRTHDAY, SOPHIE! “Remember,” Molly murmured, “we’re not stealing. We’re relocating.” “To our van.” “Temporarily forever.” Bill adjusted his fake mustache, which was made of licorice. “What if someone asks who we are?” “Say you’re the balloon inspector.” “That’s not real.” “Neither is your mustache.” A gust of wind lifted the napkin map into the goat petting area. The goat ate phase three. Bill sighed. “Abort?” Molly watched Sophie hand a cupcake to a crying toddler. She groaned. “Fine. New plan.” “We leave?” “We buy her a better present. Then steal the magician’s rabbit.” The rabbit stared. Bill swallowed. “He heard you.”
created_at
"2026-04-24T21:02:54.038Z"
4/24/2026, 9:02:54 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
677
moderation_latency
(null)
generation_time
8191
tokens_prompt
77
tokens_completion
398
native_tokens_prompt
66
native_tokens_completion
310
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
0.00963
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0b192e46874461110169ebda7e233c8197a1fee710c12c9d09"
is_byok
false
latency
284
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-1777064574-m3L8YaicBYYQD7InVTVa"
session_id
(null)
api_type
"completions"
id
"gen-1777064574-retABLr2FzGFqZ2o5IOO"
upstream_id
"resp_0b192e46874461110169ebda7e233c8197a1fee710c12c9d09"
total_cost
0.00963
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
207
87.55%
Dialogue to Total Word Ratio
Ratio: 43.96%, Deviation: 6.04%
neededClean
false
wordsTotal
207
wordsDialogue
91
92.5883%