NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXERX1SKJ4Q27X2MBPKMEP
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
12.7s
Cost:
$0.012740
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
51.52%
Dialogue to Total Word Ratio
(details)
75.6311%
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 stealing presents from children," Bill said. "From actual children." "Keep your voice down." "At a birthday party." "It's a *rich* birthday party, Bill. These kids get ponies. They won't miss a few gift bags." "What's the plan?" "You dress as the clown. I'll be the magician." "Why do you get to be the magician?" "Because I'm the brains, and brains do magic." "I don't want to be the clown." "Everyone loves the clown." "Children are terrified of clowns." "Exactly! Fear is a distraction. While they're crying, I make the presents disappear." "That's your whole trick? Stealing gifts and calling it magic?" "It's thematically appropriate." "And how do we carry it all out?" "The bouncy castle." "...The bouncy castle." "We deflate it, load the presents inside, and roll it out the front door like a giant inflatable burrito." "Molly, that's insane." "That's *genius*, Bill." "What if the parents notice?" "They're rich. They're day-drinking by noon. Trust me." "And the cake?" "What about the cake?" "Can I have some cake?" "You're stealing from toddlers and you're worried about *cake*?" "A man's gotta eat." "Fine. You can have cake. *After* the heist." "Deal. Hand me the clown nose." "That's my heart, you idiot. Wrong bag."
created_at
"2026-05-31T11:42:08.302Z"
5/31/2026, 11:42:08 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
993
moderation_latency
(null)
generation_time
12709
tokens_prompt
77
tokens_completion
361
native_tokens_prompt
93
native_tokens_completion
491
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
0.01274
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01BR2MNjpHdmZjV1PN77qwLu"
is_byok
false
latency
993
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-1780227728-TjhbNvB2RsthvhOpz2jB"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780227728-ZE1On7FYQSkYly2VhyOU"
upstream_id
"msg_01BR2MNjpHdmZjV1PN77qwLu"
total_cost
0.01274
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
51.52%
Dialogue to Total Word Ratio
Ratio: 99.02%, Deviation: 9.02%
neededClean
false
wordsTotal
205
wordsDialogue
203
75.6311%