NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE9X1S9TZQB770B1TNR4E1T
Run Details
Model:
Claude Sonnet 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.7s
Cost:
$0.004496
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
67.09%
Dialogue to Total Word Ratio
(details)
80.3677%
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 let me get this straight," Molly said, "we're robbing a six-year-old." "We're robbing a six-year-old's birthday party," Bill corrected. "Completely different moral category." "Explain that math to me, Bill." "Kids don't even like half their presents. You know how many unopened Legos end up in landfills every year?" "That's not the point and you know it." "There's a bounce house, Molly. A bounce house full of unsupervised gifts. It's basically a vault with balloons." "There's also going to be like twenty parents." "Parents who are drunk on mimosas by eleven a.m., watching a magician pull scarves out of his sleeve. Nobody's watching the present table." "Fine. What's the plan?" "I go in as the clown." "You booked yourself as the actual clown?" "Cancellation fee was outrageous. I couldn't resist." "You don't know how to make balloon animals." "I know how to make balloon 'shapes.' Kids won't know the difference." "And me?" "You're the mom who 'forgot the good camera' and needs to run to the car. Repeatedly." "That's it? That's the whole plan?" "Molly, we're stealing from children. The bar was already on the floor." "Fair point. Grab the balloons."
created_at
"2026-07-01T07:39:39.189Z"
7/1/2026, 7:39:39 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1471
moderation_latency
(null)
generation_time
8706
tokens_prompt
77
tokens_completion
323
native_tokens_prompt
93
native_tokens_completion
431
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
0.004496
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_011j8UtdJi9vgkt8cpPcLZbv"
is_byok
false
latency
1471
model_permaslug
"anthropic/claude-sonnet-5-20260630"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.17.0; linux; x64))"
http_referer
(null)
request_id
"req-1782891579-zPuox2Dhj6iFjyy5KW24"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891579-lQly1VeDAPLg65EWys2n"
upstream_id
"msg_011j8UtdJi9vgkt8cpPcLZbv"
total_cost
0.004496
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
191
67.09%
Dialogue to Total Word Ratio
Ratio: 97.95%, Deviation: 7.95%
neededClean
false
wordsTotal
195
wordsDialogue
191
80.3677%