NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1HKGCJAG738QYVT11ZC2FB
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.2s
Cost:
$0.012740
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
66.26%
Dialogue to Total Word Ratio
(details)
83.1201%
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 spoiled children." "How do you know they're spoiled?" "It's a birthday party, Bill. There's a bouncy castle." "Maybe it's rented." "Nobody rents a bouncy castle for a humble child." "Fair point. What's the plan?" "You distract them. I grab the gifts." "How do I distract twenty seven-year-olds?" "Be a clown." "I'm not dressing as a clown." "Then be a magician." "I don't know magic." "You don't need to know magic. They're seven." "What if they ask for a specific trick?" "Pull a coin from behind their ear." "What if there's no coin?" "Bring a coin, Bill." "Bring my own coin? To a robbery?" "It's an investment." "And the parents? They'll notice a grown man stealing wrapped boxes." "They'll be filming the clown." "I thought I was a magician." "Magician, clown, whatever. The point is they'll be distracted." "This feels morally complicated." "It's gift bags and remote-control cars, Bill. We'll be rich." "Rich from toys?" "Vintage toys. There's a market." "There's a market for stolen children's toys?" "There's a market for everything." "I really hate this plan." "Bring the coin, Bill."
created_at
"2026-06-01T12:12:43.798Z"
6/1/2026, 12:12:43 PM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1201
moderation_latency
95
generation_time
9104
tokens_prompt
77
tokens_completion
362
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_01HNwCu9KUmxYuXZX4ST6mVt"
is_byok
false
latency
1201
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-1780315963-bVp5qMUpqql4O1PkGhtI"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780315963-WBfoHJuL6zjGspfweM66"
upstream_id
"msg_01HNwCu9KUmxYuXZX4ST6mVt"
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
99.98%
Matches word count
n/a
neededClean
false
words
198
66.26%
Dialogue to Total Word Ratio
Ratio: 98.01%, Deviation: 8.01%
neededClean
false
wordsTotal
201
wordsDialogue
197
83.1201%