NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEA1Z5WFNHXYX10SF0DVBVE
Run Details
Model:
Claude Sonnet 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.8s
Cost:
$0.005206
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.3562%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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
Molly slid the blueprint across the table, a crayon drawing of a bounce house with "TIMMY'S 7TH BIRTHDAY" scrawled in glitter glue. "This is our target?" Bill said, squinting. "A seven-year-old's birthday party?" "Not just any party," Molly said. "Word on the street is Timmy's getting a PlayStation, a hoverboard, and—get this—an actual drone." "A drone? At seven?" "Rich kids, Bill. Keep up." Bill crossed his arms. "So what's the plan? We just walk in wearing clown suits and grab the loot?" "Please. I have a system." Molly pulled out a rubber chicken mask. "You're the entertainment. I'm the caterer's assistant." "Why do I get the chicken?" "Because chickens are trustworthy. Everyone loves a chicken." "Nobody loves a chicken, Molly." "Kids do! Now, when you're doing your act, I sneak the presents into the dessert table hollow center—" "There's a hollow center?" "I built it last night. Focus." Bill sighed, pulling the chicken mask over his head. "If we get caught, I'm blaming you." "If we get caught, we'll be outrun by a seven-year-old," Molly said. "Let's not get caught." Bill's muffled voice came through the beak. "This had better be worth it." "Trust me," Molly grinned. "That drone's paying our rent this month."
created_at
"2026-07-01T07:42:20.36Z"
7/1/2026, 7:42:20 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2384
moderation_latency
(null)
generation_time
9817
tokens_prompt
77
tokens_completion
338
native_tokens_prompt
93
native_tokens_completion
502
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
0.005206
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01BgVmNhZjnrwJPpqn2AY78d"
is_byok
false
latency
2384
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-1782891740-39xBMPNU6vcSFFgvcNlD"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891740-mf3758LHxTPt17yIFKTM"
upstream_id
"msg_01BgVmNhZjnrwJPpqn2AY78d"
total_cost
0.005206
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
98.71%
Matches word count
n/a
neededClean
false
words
206
0.00%
Dialogue to Total Word Ratio
Ratio: 73.81%, Deviation: 23.81%
neededClean
false
wordsTotal
210
wordsDialogue
155
49.3562%