NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PXF2XHYW13SWK9GM7DW46
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
19.9s
Cost:
$0.037200
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
78.65%
Dialogue to Total Word Ratio
(details)
89.3275%
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
“Bill, remember: we’re party entertainers, not burglars until after the jelly.” “Molly, I’m wearing a raccoon mask.” “Children love woodland themes.” “It’s a pirate party.” “Then you’re a sea raccoon. Now, objective: presents.” “All of them?” “Every glittery, ribboned, suspiciously rectangular one.” “What if one is socks?” “Then we donate it to your tragic ankles.” “Molly, these are children.” “Rich children. Last year the birthday boy got a pony with highlights.” “Still, stealing teddy bears feels low.” “We’re not stealing teddy bears; we’re liberating evidence of capitalism.” “Your conscience talks fancy when scared.” “My conscience is in the van eating crisps. Listen: you distract them with balloon animals.” “I only know worm.” “Make twenty worms and call it a safari.” “And you?” “I mingle near the gift mountain, laugh like an aunt, and identify the premium parcels.” “Then what?” “We leave with the magician’s trunk.” “There’s a magician?” “There will be when I put you in a cape.” “I hate capes. They make my neck look dramatic.” “That’s the point.” A squeal rose from the garden. “They’re singing.” “Good. Nobody suspects criminals during ‘Happy Birthday.’” “Except everyone staring at the sea raccoon.” “Smile, Bill.” “Raccoons don’t smile.” “Tonight, they improvise.”
created_at
"2026-04-24T21:39:13.131Z"
4/24/2026, 9:39:13 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
16929
moderation_latency
(null)
generation_time
19727
tokens_prompt
77
tokens_completion
433
native_tokens_prompt
66
native_tokens_completion
1229
native_tokens_completion_images
0
native_tokens_reasoning
926
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
0.0372
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_02031f564a1011550169ebe30138908195b56739d266f714d8"
is_byok
false
latency
235
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-1777066753-RrUBqa8BKcxIRXU8cI3k"
session_id
(null)
api_type
"completions"
id
"gen-1777066753-WfJXPFPzEpVfQZV1FoDz"
upstream_id
"resp_02031f564a1011550169ebe30138908195b56739d266f714d8"
total_cost
0.0372
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
78.65%
Dialogue to Total Word Ratio
Ratio: 97.00%, Deviation: 7.00%
neededClean
false
wordsTotal
200
wordsDialogue
194
89.3275%