NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEA229YGYJ9JJ2H6MC68VHZ
Run Details
Model:
Claude Sonnet 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.0s
Cost:
$0.005026
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
21.6892%
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 popcorn and desperation, which Bill figured was appropriate given the caliber of their operation lately. He spread the blueprints across the card table, if you could call a birthday party's floor plan "blueprints." Molly leaned over his shoulder, chewing gum like she was trying to kill it personally. "Six-year-old's birthday party," Bill said, tapping the paper. "Bounce house perimeter, cake table's the main vault, and presents are stacked by the sliding glass door. Practically an invitation." Molly snorted. "We're stealing candy from a baby, Bill. Literally. There will be babies." "They're six. They have insurance. Probably." She studied the layout, unimpressed. The clown entertainment schedule was color-coded, which felt like overkill for a heist involving juice boxes and inflatable castles. Bill had planned bank jobs with less detail. "What's our cover?" Molly asked, popping her gum. "I'm the balloon guy. You're catering." "I don't know how to cater." "You don't know how to make balloon animals either, but here we are." Molly grabbed a fake mustache from the pile of costumes, holding it up with visible skepticism, like it might bite her. Outside, a minivan pulled up, unloading exactly the kind of oblivious rich parents who left garage doors open and expensive gifts unguarded. Showtime, Bill thought, and grinned like an idiot.
created_at
"2026-07-01T07:42:23.561Z"
7/1/2026, 7:42:23 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1822
moderation_latency
(null)
generation_time
9947
tokens_prompt
77
tokens_completion
362
native_tokens_prompt
93
native_tokens_completion
484
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
0.005026
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01Frohoqrug9WRunAeyK2xCb"
is_byok
false
latency
1822
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-1782891743-wDhwaNzgjkHr83u3lkih"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891743-Xic6EIxhtUH0dev6gf5m"
upstream_id
"msg_01Frohoqrug9WRunAeyK2xCb"
total_cost
0.005026
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
43.38%
Matches word count
n/a
neededClean
false
words
217
0.00%
Dialogue to Total Word Ratio
Ratio: 32.73%, Deviation: 22.73%
neededClean
false
wordsTotal
220
wordsDialogue
72
21.6892%