NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE8W112M02Q0EHP3V2JJCT5
Run Details
Model:
Claude Sonnet 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
8.2s
Cost:
$0.004886
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
37.5778%
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 of stale popcorn and desperation, which felt about right given what Molly and Bill were about to attempt. Spread across the folding table between them was a hand-drawn map of the Hendricks' backyard, complete with a bounce house marked in red marker labeled "DANGER ZONE." "So we go in through the hedge," Bill said, tracing a route with a greasy finger, "past the clown—" "There's a clown?" Molly's eyebrows shot up. "There's always a clown, Molly. Focus." She rubbed her temples. Six years of high-stakes jewelry heists, art forgery scandals, and one memorable incident involving a stolen yacht, and here she was, thirty-seven years old, planning to steal birthday presents from seven-year-olds. "The bag with the dinosaur wrapping paper is the target," Bill continued. "Inside, allegedly, is a gaming console worth more than my car." "Your car is a Datsun held together with duct tape." "Exactly my point." Molly stared at the map, at the tiny stick figure labeled "BOUNCER" standing guard near the present table, at the elaborate escape route through someone's vegetable garden. She thought about her mother, about disappointment, about the various life choices that had led to this moment. "We're really doing this," she said. It wasn't quite a question. Bill grinned. "Cake first, though. Obviously."
created_at
"2026-07-01T07:21:37.07Z"
7/1/2026, 7:21:37 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1595
moderation_latency
(null)
generation_time
8182
tokens_prompt
77
tokens_completion
351
native_tokens_prompt
93
native_tokens_completion
470
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
0.004886
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01Dm5dnQUaYPauRwhmwHDr67"
is_byok
false
latency
1594
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-1782890497-3uIO8v0ZbtdaePBL6Kbb"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890497-2on9NMzmWuMHEhjtQPJw"
upstream_id
"msg_01Dm5dnQUaYPauRwhmwHDr67"
total_cost
0.004886
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
75.16%
Matches word count
n/a
neededClean
false
words
213
0.00%
Dialogue to Total Word Ratio
Ratio: 34.86%, Deviation: 24.86%
neededClean
false
wordsTotal
218
wordsDialogue
76
37.5778%