NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEAEFGVX8GSZ7J9DA11XGJY
Run Details
Model:
Claude Sonnet 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.6s
Cost:
$0.005076
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
20.19%
Matches word count
(details)
53.56%
Dialogue to Total Word Ratio
(details)
36.8768%
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 the plan," Bill whispered, "is we dress as clowns." "Bill. No." "Why not? Clowns are invisible at kids' parties. Nobody questions a clown." "Nobody trusts a clown either. Kids scream at clowns." "Fine. Magicians, then." "We don't know magic." "I know one trick. The disappearing quarter." "We're stealing presents, not doing a talent show." "Exactly! We do the trick, everyone's distracted, presents disappear too. Same principle." "That's not a principle, that's a coincidence with extra steps." "Do you have a better idea, Molly?" "Yes. We say we're the caterers. Walk in, load the gifts into the 'dessert cart,' walk out." "There's a dessert cart?" "There will be once we steal one." "So we're stealing a cart to steal presents." "Correction: borrowing a cart to acquire presents." "You always make theft sound like brunch." "That's why I'm in charge of the words and you're in charge of lifting things." "I lifted that safe last week." "You dropped that safe last week." "It landed safely." "On your foot." "Softly. On my foot. Softly." "Just get the balloons, Bill. We're clowns now."
created_at
"2026-07-01T07:49:10.312Z"
7/1/2026, 7:49:10 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2958
moderation_latency
(null)
generation_time
8598
tokens_prompt
77
tokens_completion
372
native_tokens_prompt
93
native_tokens_completion
489
native_tokens_completion_images
(null)
native_tokens_reasoning
58
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
0.005076
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01HRFSUfRGj5ZmMrfGderWuF"
is_byok
false
latency
1611
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-1782892150-fCzCEn5MSznzFOse28zq"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782892150-rXk9DY8aLFEqMVQvzpYt"
upstream_id
"msg_01HRFSUfRGj5ZmMrfGderWuF"
total_cost
0.005076
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
20.19%
Matches word count
n/a
neededClean
false
words
180
53.56%
Dialogue to Total Word Ratio
Ratio: 98.89%, Deviation: 8.89%
neededClean
false
wordsTotal
180
wordsDialogue
178
36.8768%