NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEAFPDK2MQGYFW54MNSMQ7Z
Run Details
Model:
Claude Sonnet 5
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
9.1s
Cost:
$0.004946
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
49.9995%
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 spread the blueprint across the table, jabbing a finger at the little square marked "GIFT TABLE." "Bill, look at this. Six-year-old's birthday party. Balloons everywhere. Nobody's watching the presents." Bill leaned back in his chair, unimpressed. "You want us to rob a kid's birthday party?" "Not rob. Liberate. Those presents are basically unguarded cash." Molly tapped the paper again. "There's a clown for security, Bill. A clown." "A clown could still see us." "Clowns can't see past their own noses, that's science." Molly grinned. "We go in during the piñata. Everyone's distracted, swinging sticks, screaming about candy. We slide in, grab the loot, slide out." Bill crossed his arms. "And if some kid notices?" "Then we say we're the entertainment. Magicians. Nobody questions magicians." "You don't even own a top hat." "I'll borrow one. Focus, Bill." He sighed, rubbing his temples. "This is beneath us. We robbed a bank last month." "And we barely got out with our lives. This is a birthday party. Worst case, someone hits us with a Nerf bat." Bill considered this, then smirked. "Fine. But I'm not wearing a clown nose." "Deal," Molly said, already rolling up the blueprint. "Bring the van. Piñata's at three."
created_at
"2026-07-01T07:49:50.143Z"
7/1/2026, 7:49:50 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2139
moderation_latency
(null)
generation_time
9004
tokens_prompt
77
tokens_completion
332
native_tokens_prompt
93
native_tokens_completion
476
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
0.004946
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_019PGLmnioebbXqTPD1UJswq"
is_byok
false
latency
2139
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-1782892190-AXTRIS9qlUrnDmYLaW2R"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782892190-2SMItKImBGAaJLWdkAxF"
upstream_id
"msg_019PGLmnioebbXqTPD1UJswq"
total_cost
0.004946
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
100.00%
Matches word count
n/a
neededClean
false
words
201
0.00%
Dialogue to Total Word Ratio
Ratio: 75.37%, Deviation: 25.37%
neededClean
false
wordsTotal
203
wordsDialogue
153
49.9995%