NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWEA3YFF8A0YNNXNQQVG23G6
Run Details
Model:
Claude Sonnet 5 (Reasoning, Low)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
8.3s
Cost:
$0.004686
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.98%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3860%
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, walk me through it again." "We go in as clowns." "We are not going in as clowns." "Why not? Clowns are trusted figures at children's parties." "Clowns are terrifying figures at children's parties. Half these kids will scream. Someone calls the cops." "Fine. Magicians, then." "Do you know any magic?" "I know how to make presents disappear." "That's stealing, Bill, not magic." "Same skill set, different marketing." "We need a real plan. Something quiet." "I've got balloons." "Balloons?" "Everybody loves the balloon guy. Nobody questions the balloon guy. I twist a few dogs, work the room, you slip out back with the loot." "And when the birthday kid asks the balloon guy for a poodle and you make a lumpy snake?" "I panic gracefully. I'm good at panicking gracefully." "You once panicked so gracefully you set off a car alarm with your own scream." "That was a stressful heist, Molly." "It was a bake sale." "There were a lot of cupcakes on the line." "Just get the sack open when I hand you the presents. No talking to children. No eye contact with parents." "What about the cake?" "We are not stealing the cake, Bill." "One slice." "Bill." "For morale."
created_at
"2026-07-01T07:43:25.179Z"
7/1/2026, 7:43:25 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1683
moderation_latency
(null)
generation_time
8240
tokens_prompt
77
tokens_completion
337
native_tokens_prompt
93
native_tokens_completion
450
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
0.004686
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01RTNPYWmQCbEymKjwHmwR3q"
is_byok
false
latency
1683
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-1782891805-VlBaFSTHnBdPxUjIIDxi"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782891805-hyPJM3UsWqCGswDEydh6"
upstream_id
"msg_01RTNPYWmQCbEymKjwHmwR3q"
total_cost
0.004686
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
99.98%
Matches word count
n/a
neededClean
false
words
202
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
202
wordsDialogue
202
68.3860%