NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXE1EFBEF6A4XS7TXP34CS
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.0s
Cost:
$0.012940
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
66.53%
Dialogue to Total Word Ratio
(details)
83.2236%
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
"So we're really doing this?" Bill whispered. "Stealing from kids?" "Not stealing. Liberating," Molly said. "Those presents are wasted on six-year-olds." "There's gonna be a clown." "I'm not afraid of clowns, Bill." "I am! Deeply!" "Focus. We go in dressed as the entertainment. You're the magician." "Why am I the magician?" "Because you've got the hat." "It's a beanie!" "Close enough. I'll be the face painter. Nobody suspects the face painter." "And then what?" "Then, while you're pulling rabbits out of nowhere, I load the gifts into the van." "I don't have a rabbit." "Improvise! Pull out a sock or something." "Kids hate socks, Molly." "So do I, but here we are." "What if the parents recognize us?" "From where? Our last heist was a yarn store. Grandmas don't throw birthday parties." "This one might." "Bill." "Yes?" "Trust the plan." "The plan is theft and clown trauma." "The plan is genius." "What about the cake?" "What about it?" "Can we take the cake?" "We're not taking the cake." "But—" "Fine! We take the cake." "And the bouncy castle?" "It won't fit in the van, Bill." "We deflate it." "...Okay, that's actually brilliant." "See? Now who's the magician?"
created_at
"2026-05-31T11:41:44.284Z"
5/31/2026, 11:41:44 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
971
moderation_latency
(null)
generation_time
9986
tokens_prompt
77
tokens_completion
354
native_tokens_prompt
93
native_tokens_completion
499
native_tokens_completion_images
(null)
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
"end_turn"
service_tier
"default"
usage
0.01294
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_012NDdhpdXLPTUE4zy8vFF76"
is_byok
false
latency
971
model_permaslug
"anthropic/claude-4.8-opus-20260528"
provider_name
"Anthropic"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.16.0; linux; x64))"
http_referer
(null)
request_id
"req-1780227704-5FLJE7BDXcMQcLwy5jXj"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780227704-jiTNSm2z4RzImXQ6XH0U"
upstream_id
"msg_012NDdhpdXLPTUE4zy8vFF76"
total_cost
0.01294
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
66.53%
Dialogue to Total Word Ratio
Ratio: 97.99%, Deviation: 7.99%
neededClean
false
wordsTotal
199
wordsDialogue
195
83.2236%