NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE94NY0BJWK5CEE74NCZEGJ
Run Details
Model:
Claude Sonnet 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
9.1s
Cost:
$0.005346
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
67.09%
Dialogue to Total Word Ratio
(details)
82.8991%
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
"Okay," Bill said, "walk me through this again." "We go in dressed as clowns," Molly said. "We already established the clowns are a problem." "Why is it a problem?" "Because children *scream* at clowns, Molly. It's a documented phenomenon." "Not at *funny* clowns." "Are you funny?" "I'm hilarious." "You once made a toddler cry by doing a magic trick." "That coin was supposed to disappear!" "It disappeared into his eye socket!" "Minor miscalculation." "So no clowns." "Fine. Balloon animal guy." "Same problem, different hat." "Bill, what's your genius plan then?" "We pose as the caterers. Sneak in, grab the presents, sneak out." "With what food?" "...Cupcakes?" "From where?" "The grocery store." "They're gonna know we didn't make cupcakes for forty kids in a Honda Civic." "They will be *distracted* by how good the cupcakes are." "Bill." "What." "There's a bouncy castle." "So?" "So we could just bounce in as party guests, nobody questions bouncing." "We're thirty-seven years old." "I have a youthful face." "You have a mustache." "It's ironic." "Nothing about grand larceny is ironic, Molly." "Fine! Clowns, cupcakes, or bouncing—pick one before the piñata starts." "...Bouncing. But I'm not wearing a bib."
created_at
"2026-07-01T07:26:20.621Z"
7/1/2026, 7:26:20 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1349
moderation_latency
(null)
generation_time
9070
tokens_prompt
77
tokens_completion
366
native_tokens_prompt
93
native_tokens_completion
516
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
0.005346
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_013wsVdW9NR8gDsTpcHyS8Cw"
is_byok
false
latency
1348
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-1782890780-h0E8lMIqw6VF01iD3KA1"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890780-yqKLShRzDj6EeTAgdiWe"
upstream_id
"msg_013wsVdW9NR8gDsTpcHyS8Cw"
total_cost
0.005346
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
194
67.09%
Dialogue to Total Word Ratio
Ratio: 97.95%, Deviation: 7.95%
neededClean
false
wordsTotal
195
wordsDialogue
191
82.8991%