NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-06-01-01KT1GSGDHFDJV72F0SCKWQGBM
Run Details
Model:
Claude Opus 4.8 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.8s
Cost:
$0.012890
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
51.66%
Dialogue to Total Word Ratio
(details)
75.8317%
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?" Molly asked. "Simple. We dress as clowns." "Clowns? Bill, I hate clowns." "Everyone hates clowns. That's why nobody looks at them too closely." "And the presents?" "Stacked by the bouncy castle. We grab them during the piñata." "Why the piñata?" "Because, Molly, when forty kids are swinging a bat blindfolded, chaos reigns. Nobody notices two clowns wheeling out a wagon." "A wagon." "A red one. With balloons tied to it. Disguise it as part of the act." "You've thought about this." "I've thought of nothing else for three days." "That's deeply concerning." "The cake comes out at two. That's our window." "And if a parent stops us?" "You honk your nose and juggle. Buys us thirty seconds." "I can't juggle." "Then you'd better learn by Saturday." "Bill, this is a six-year-old's birthday party." "With premium loot. iPads, Bill. Little kids get iPads now." "That's tragic." "That's opportunity." "What if we get caught?" "We won't. But if we do, we cry. People can't arrest a crying clown." "That's the dumbest plan I've ever heard." "Is it working?" "...A little." "Grab your wig." "Fine. But I'm not wearing the giant shoes." "The shoes are non-negotiable, Molly."
created_at
"2026-06-01T11:58:31.863Z"
6/1/2026, 11:58:31 AM
model
"anthropic/claude-4.8-opus-20260528"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1119
moderation_latency
(null)
generation_time
9783
tokens_prompt
77
tokens_completion
351
native_tokens_prompt
93
native_tokens_completion
497
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
0.01289
router
(null)
provider_responses
0
endpoint_id
"b0d3beaa-5ff7-4666-a749-b1bb2b14c916"
id
"msg_01KDhj1B999DwQu2rMf6CZHC"
is_byok
false
latency
1119
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-1780315111-VXwdUvqLb4EQfOOVAEeL"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1780315111-RZVfOiSgvtpKDYh1KtEH"
upstream_id
"msg_01KDhj1B999DwQu2rMf6CZHC"
total_cost
0.01289
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Anthropic"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
51.66%
Dialogue to Total Word Ratio
Ratio: 99.01%, Deviation: 9.01%
neededClean
false
wordsTotal
203
wordsDialogue
201
75.8317%