NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0NSSWPKAZPA41CY97S472B
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
23.9s
Cost:
$0.046380
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.51%
Dialogue to Total Word Ratio
(details)
99.7551%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 flattened the party invitation on the table. “Listen, Bill, at three o’clock the jelly arrives, at three-oh-five the magician loses a rabbit, and at three-ten we glide in.” “Glide? I wore squeaky shoes.” “Then squeak confidently.” “What if the children notice us stealing all the presents?” “We’re not stealing; we’re temporarily relocating joy.” “To our van.” “To our van-shaped annex of opportunity.” “Children cry loudly, Molly.” “So do police sirens, but you never complain until they’re close.” “I’m just saying, birthday parties have defenses. Balloons. Grandmothers. Sticky hands.” “I have neutralized sticky hands.” “How?” “Wet wipes and flattery.” “What about the clown?” “If he’s real, we avoid eye contact. If he’s hired, we bribe him with cake.” “Cake is evidence.” “Cake is morale.” Bill peered at the invitation. “It says ‘Princess Lottie turns six.’ We’re robbing Princess Lottie?” “Don’t humanize the mark.” “She drew a unicorn in crayon.” “Fine. We steal only the loud presents.” “Drums, whistles, robot dogs?” “Exactly. We’re public servants.” “And the quiet presents?” “We leave a note: ‘Dear Princess, you’re welcome. Love, sensible criminals.’” Bill sighed. “I’ll bring the wipes.” “And a card.” “Why?” “Villains need manners.” “Fine. Glitter?” “Absolutely not. We’re thieves, not monsters.”
created_at
"2026-04-24T21:19:44.541Z"
4/24/2026, 9:19:44 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
22134
moderation_latency
(null)
generation_time
22668
tokens_prompt
77
tokens_completion
582
native_tokens_prompt
66
native_tokens_completion
1535
native_tokens_completion_images
0
native_tokens_reasoning
1212
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
0.04638
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0f88c1952280adbc0169ebde70a0dc8197a77108886603f125"
is_byok
false
latency
271
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-1777065584-xbUHg0XUYSsRfS2LUfxq"
session_id
(null)
api_type
"completions"
id
"gen-1777065584-0lshXTJveFyf1TV12XGY"
upstream_id
"resp_0f88c1952280adbc0169ebde70a0dc8197a77108886603f125"
total_cost
0.04638
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
99.51%
Dialogue to Total Word Ratio
Ratio: 92.65%, Deviation: 2.65%
neededClean
false
wordsTotal
204
wordsDialogue
189
99.7551%