NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE9QZP0GPK0RGTQDR63RGT3
Run Details
Model:
Claude Sonnet 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.6s
Cost:
$0.004556
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
27.17%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
31.9769%
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
"Bill, we need to talk about the plan." "What plan? We walk in, we grab the presents, we walk out. Boom. Done." "It's a seven-year-old's birthday party, not a bank." "Same thing! There's a vault—it's called a 'present table'—and it's guarded." "Guarded by who, Bill? A clown?" "Exactly! Have you SEEN clowns? Terrifying. Big shoes, painted smiles, honking noses. I don't trust anything that honks." "So your plan is to just... avoid the clown?" "My plan is we dress as clowns. Blend in. Nobody questions a third clown at a kids' party." "There's already a clown booked?" "There's always a clown booked, Molly. It's the law of children's parties." "And when the real clown shows up?" "We say he's an imposter. Kids love drama. Very educational." "This is insane." "You got a better idea?" "Yes! We're pest control! 'Ma'am, we got reports of raccoons near your gift table, gonna need everyone to clear the yard for safety.'" "...Molly, that's actually brilliant." "Thank you." "Way better than my clown thing." "Obviously." "Still bringing the honking nose, though." "Why?!" "For luck."
created_at
"2026-07-01T07:36:53.193Z"
7/1/2026, 7:36:53 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1889
moderation_latency
(null)
generation_time
8528
tokens_prompt
77
tokens_completion
310
native_tokens_prompt
93
native_tokens_completion
437
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
0.004556
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01NkpMV56uKDd99xKJ9sgxN3"
is_byok
false
latency
1889
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-1782891413-rnIhqNM7m4RYB187y4gv"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891413-bQAnbHSTOhFvQJiTDVxE"
upstream_id
"msg_01NkpMV56uKDd99xKJ9sgxN3"
total_cost
0.004556
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
27.17%
Matches word count
n/a
neededClean
false
words
181
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
183
wordsDialogue
183
31.9769%