NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEA37V7NGRF3DXPYX4G8FJS
Run Details
Model:
Claude Sonnet 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
9.9s
Cost:
$0.005096
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
45.2419%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
The warehouse smelled like stale beer and ambition, which suited Molly and Bill just fine. Spread across the table between them was a hand-drawn map of the Hendricks' backyard, complete with a suspiciously accurate rendering of a bounce house labeled "DANGER ZONE." "Explain to me again," Bill said, squinting at the paper, "why we're robbing an eight-year-old's birthday party." Molly tapped the map with authority. "Because, Bill, nobody suspects a clown." "You're not a clown. You're wearing a raccoon costume." "Raccoons are the working man's clown." Bill rubbed his temples. Their entire criminal partnership had been built on nights like this—too much coffee, not enough sleep, and Molly's unwavering belief that petty theft required elaborate cover stories. Still, the presents would be unguarded, piled high beneath a banner that screamed "HAPPY BIRTHDAY TIMMY!" in balloon letters. Cash, gift cards, maybe a bicycle if they were lucky. "The parents will be distracted by the magician," Molly continued, sliding a finger along her diagram. "That's our window. In, out, gone before the cake's even cut." "And if a kid sees us?" Molly grinned beneath her raccoon mask, eyes gleaming with the confidence of someone who had clearly never met a determined seven-year-old. "Bill," she said, "we outrun cops for a living."
created_at
"2026-07-01T07:43:02Z"
7/1/2026, 7:43:02 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1481
moderation_latency
(null)
generation_time
9909
tokens_prompt
77
tokens_completion
348
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
0.005096
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01Y7M4SMiiobNLbp4Y8pKFx5"
is_byok
false
latency
1481
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-1782891782-YUpFNjPu6vnUPg4oaIzg"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891782-j6asgudAaw5PoHK0oyPL"
upstream_id
"msg_01Y7M4SMiiobNLbp4Y8pKFx5"
total_cost
0.005096
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
90.48%
Matches word count
n/a
neededClean
false
words
210
0.00%
Dialogue to Total Word Ratio
Ratio: 39.07%, Deviation: 29.07%
neededClean
false
wordsTotal
215
wordsDialogue
84
45.2419%