NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXQZ14J7W75VJJ2XPBAR3M
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.6s
Cost:
$0.013915
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
95.99%
Matches word count
(details)
65.34%
Dialogue to Total Word Ratio
(details)
80.6628%
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 how do we get in?" Bill asked. "We dress as clowns," Molly said. "Clowns? I hate clowns." "Everybody hates clowns. That's why nobody looks at them too closely." "And the presents?" "Big sack. Clowns always carry big sacks." "That's Santa." "Santa, clowns, same energy. Nobody questions a man with a sack." "What about the parents?" "Distracted. Cake, juice boxes, forty screaming children. We're invisible." "And if a kid recognizes us?" "From where, Bill? Do you frequent children's parties?" "I have a nephew." "Will your nephew be there?" "...No." "Then we're fine." "What if they want balloon animals?" "Then you make a balloon animal." "I can't make balloon animals!" "Make a snake. A snake is just one balloon." "That's lazy." "It's a children's party, not the Louvre. Lower your standards." "And the getaway?" "Ice cream truck. Parked out front. Nobody suspects an ice cream truck." "We don't have an ice cream truck." "We will by Saturday." "You're stealing an ice cream truck to steal birthday presents?" "It's called commitment, Bill." "This is the dumbest plan you've ever had." "Worse than the aquarium?" "...The aquarium was pretty bad." "So we're agreed. Clowns, sacks, ice cream truck." "Fine. But I'm not making balloon animals." "Make the snake." "Fine. One snake."
created_at
"2026-05-31T11:47:09.487Z"
5/31/2026, 11:47:09 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
965
moderation_latency
147
generation_time
9454
tokens_prompt
77
tokens_completion
381
native_tokens_prompt
93
native_tokens_completion
538
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
0.013915
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01QNq2hqS111eXsmmELLh9KD"
is_byok
false
latency
965
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-1780228029-a8fKypDC6wC1nHhlOK4i"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780228029-gbzrHYv6fTWan9MYrBg0"
upstream_id
"msg_01QNq2hqS111eXsmmELLh9KD"
total_cost
0.013915
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
95.99%
Matches word count
n/a
neededClean
false
words
208
65.34%
Dialogue to Total Word Ratio
Ratio: 98.08%, Deviation: 8.08%
neededClean
false
wordsTotal
208
wordsDialogue
204
80.6628%