NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEA55QY4BTTMPJVXCHDW5X0
Run Details
Model:
Claude Sonnet 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.0s
Cost:
$0.004466
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
14.30%
Matches word count
(details)
68.88%
Dialogue to Total Word Ratio
(details)
41.5890%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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
"So let me get this straight," Bill said. "We're robbing a seven-year-old's birthday party." "Eight-year-old," Molly said. "And we're not robbing her. We're robbing her guests. There's a difference." "There's really not." "Bill. There's a table full of unopened presents. Nobody's watching them. It's basically a bank vault made of wrapping paper." "With a bouncy castle next to it." "Which is our exit strategy." "You want to escape through a bouncy castle." "I want to escape *over* a bouncy castle. Keep up." "There's gonna be like thirty kids there, Molly." "So?" "So thirty kids is thirty witnesses. And they scream. Loudly. About everything." "They also can't identify faces past 'big' and 'scary,' so we're basically invisible." "You're five foot two." "I meant you." "I hate this plan." "You loved this plan an hour ago." "An hour ago I thought it was a jewelry store." "Same energy. Sparkly boxes, ribbons instead of alarms." "There's a clown, Molly." "Then you'll blend right in." "I'm not wearing the wig again." "The wig is the plan, Bill. The wig is the *whole* plan."
created_at
"2026-07-01T07:44:05.386Z"
7/1/2026, 7:44:05 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2383
moderation_latency
(null)
generation_time
8976
tokens_prompt
77
tokens_completion
307
native_tokens_prompt
93
native_tokens_completion
428
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
0.004466
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01Qf9xeoqKbouNMReYMU7BPQ"
is_byok
false
latency
2383
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-1782891845-zCbV1U7nitQckBso6PRI"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891845-O70HmesWyTGxQruTg9n3"
upstream_id
"msg_01Qf9xeoqKbouNMReYMU7BPQ"
total_cost
0.004466
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
14.30%
Matches word count
n/a
neededClean
false
words
179
68.88%
Dialogue to Total Word Ratio
Ratio: 97.81%, Deviation: 7.81%
neededClean
false
wordsTotal
183
wordsDialogue
179
41.5890%