NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE8WF2QR55Z5TJGSKEQ8711
Run Details
Model:
Claude Sonnet 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.8s
Cost:
$0.004606
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
14.30%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
7.1507%
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, which was actually a napkin with a crayon drawing of a bouncy castle. "This is not a blueprint, Bill." "It's Timmy's blueprint. I paid his sister four dollars for it." "You bribed a six-year-old." "She drives a hard bargain." Molly rubbed her temples. "Fine. Walk me through it." "We go in dressed as the clowns." "There's already a clown booked." "We go in as *extra* clowns. Nobody questions extra clowns, Molly. That's basic party logistics." "And when the real clown shows up?" "Two clowns, one bouncy castle. It's a mystery. Kids love mysteries." Molly stared at him. "We are stealing birthday presents from a seven-year-old." "Eight-year-old. Read the invitation." "That makes it worse, Bill." "Does it? Does it really?" She groaned, snatching the crayon map. "The presents are on a table by the cake, guarded by—according to this napkin—a dog named Sprinkles." "Sprinkles is a menace. Timmy's sister says he bites." "Then what's the plan for Sprinkles?" "Bacon." "That's not a plan, that's a snack." "It's both, Molly. It's both."
created_at
"2026-07-01T07:21:51.457Z"
7/1/2026, 7:21:51 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1687
moderation_latency
(null)
generation_time
7764
tokens_prompt
77
tokens_completion
307
native_tokens_prompt
93
native_tokens_completion
442
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
0.004606
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_0118fGjGUtYCq6LeL1JfNrYR"
is_byok
false
latency
1687
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-1782890511-lN7ElOSM2MoKLJV8cSvg"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890511-amye2RDdpBRzOt3pAcVh"
upstream_id
"msg_0118fGjGUtYCq6LeL1JfNrYR"
total_cost
0.004606
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
0.00%
Dialogue to Total Word Ratio
Ratio: 81.62%, Deviation: 31.62%
neededClean
false
wordsTotal
185
wordsDialogue
151
7.1507%