NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0NYA20KT0N0G57DM5EE00N
Run Details
Model:
GPT-5.5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
27.6s
Cost:
$0.048840
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
99.74%
Dialogue to Total Word Ratio
(details)
99.8689%
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 unfolded the invitation like a treasure map, except it smelled of jam and glitter. Bill squinted at the crayon castle printed beside the words Princess Poppy's Seventh Birthday. "Guards?" he whispered. "Two Labradors and a grandmother with a whistle," Molly said. "Deadly." "Focus, Bill. The presents are stacked by the bouncy castle." "Inside enemy territory." "Inside a rented unicorn marquee." "Same thing, with frosting." They crouched behind a hedge while shrieks of children sailed over it like tiny police sirens. Molly wore a caterer's apron; Bill wore a balloon hat he'd inflated by accident and now feared. "What's our cover?" he asked. "We are entertainers." "I don't entertain. I alarm." "Then you're perfect. Distract them." "With what, existential dread?" "With balloon animals." Bill looked at his hat. "I know one shape: regret." A small boy appeared at the gate, icing on his chin. "Are you the magicians?" Molly smiled so hard her cheeks squeaked. "Absolutely." Bill leaned close. "Molly, I can't do magic." "Yes you can. Make those presents disappear." "Do we still steal them?" "After applause? Never. We invoice. And maybe one cupcake each for expenses. Obviously." Bill produced a rubber chicken; the children cheered. Molly bowed.
created_at
"2026-04-24T21:22:12.179Z"
4/24/2026, 9:22:12 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
26026
moderation_latency
(null)
generation_time
26585
tokens_prompt
77
tokens_completion
465
native_tokens_prompt
66
native_tokens_completion
1617
native_tokens_completion_images
0
native_tokens_reasoning
1325
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
0.04884
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0cd55b674d263f4a0169ebdf044f4481969a3a3d03017fbc23"
is_byok
false
latency
437
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-1777065732-SMFr4aHT9stW7glUz1j9"
session_id
(null)
api_type
"completions"
id
"gen-1777065732-WN0eYANJ45xtdXviNsF5"
upstream_id
"resp_0cd55b674d263f4a0169ebdf044f4481969a3a3d03017fbc23"
total_cost
0.04884
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
99.74%
Dialogue to Total Word Ratio
Ratio: 47.74%, Deviation: 2.26%
neededClean
false
wordsTotal
199
wordsDialogue
95
99.8689%