NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-31-01KSYXGWFD74QH0YA9SES8GGZ7
Run Details
Model:
Claude Opus 4.8 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.3s
Cost:
$0.013290
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
78.98%
Dialogue to Total Word Ratio
(details)
89.4822%
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 asked. "We're really doing this," Molly said. "Stealing presents. From children." "From a child. Singular. One spoiled birthday boy." "That's worse, somehow." "His name is Maxwell. He's turning seven. His parents bought him a pony." "A pony?" "A pony, Bill. These people have disposable ponies." "Okay, but how do we get in?" "Simple. You're the clown." "I'm the what?" "The entertainment. Big shoes, red nose, the whole disaster. You distract the kids." "And you?" "I'm the magician's assistant. While you juggle, I make the gift table disappear." "Into where?" "Into the van. Behind the bouncy castle." "There's a bouncy castle?" "There's always a bouncy castle." "What if a kid recognizes me?" "From where, Bill? Your extensive children's television career?" "I did a cereal commercial in 1998." "Nobody remembers that." "My mother does." "Your mother isn't invited to Maxwell's party. Focus." "And the presents?" "We grab everything wrapped. Sort it later." "What if some of it's socks?" "Then we donate the socks and keep the PlayStation." "There's a PlayStation?" "Bill, there's a pony. There's definitely a PlayStation." "Okay," Bill said. "I'm in." "Good. Now try the nose on." "It honks." "That's the point."
created_at
"2026-05-31T11:43:17.497Z"
5/31/2026, 11:43:17 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1028
moderation_latency
(null)
generation_time
9222
tokens_prompt
77
tokens_completion
371
native_tokens_prompt
93
native_tokens_completion
513
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
0.01329
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_013htJo6vzCJC6BdXfZEDA4V"
is_byok
false
latency
1028
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-1780227797-mIWkfsFMEYeDV0MTPTS6"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780227797-HNuLI79nRY7bZtugFzU2"
upstream_id
"msg_013htJo6vzCJC6BdXfZEDA4V"
total_cost
0.01329
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.98%
Matches word count
n/a
neededClean
false
words
198
78.98%
Dialogue to Total Word Ratio
Ratio: 96.97%, Deviation: 6.97%
neededClean
false
wordsTotal
198
wordsDialogue
192
89.4822%