NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-01-01KWE8VDDSMVZMQMBMSY75GA13
Run Details
Model:
Claude Sonnet 5 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
10.3s
Cost:
$0.005066
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
0.00%
Dialogue to Total Word Ratio
(details)
43.1902%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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
The warehouse smelled of stale popcorn and desperation, which suited Bill just fine since he smelled roughly the same after three days without a shower. He spread the blueprints across a crate, jabbing a finger at a crudely drawn bounce house. "Timmy Fletcher turns seven Saturday," Molly said, tapping her cigarette against an ashtray shaped like a clown's head, which she found deeply unsettling but refused to throw away. "Forty-three presents on the registry. We're talking Xboxes, drones, some ungodly amount of Legos." Bill squinted at the diagram. "This says there's a magician." "Ronald the Magnificent. Booked for two to three." "That's our window." "That's our window." Bill straightened, adjusting his fake mustache for the ninth time that hour. "We go in as balloon animal specialists. Nobody questions a man with a mustache and a bag of balloons." "Everyone questions that man, Bill." "Fine. Face painters, then." Molly stared at him. "You can't draw a straight line." "I'll do abstract art. Tell the kids it's 'expressive.'" She sighed, crushing her cigarette into the clown's forehead. "We stick to the plan. You distract the parents. I load the presents into the van disguised as the ice cream truck." "And if someone notices forty-three presents missing?" "They'll blame Ronald." Bill grinned. "Poor bastard."
created_at
"2026-07-01T07:21:16.998Z"
7/1/2026, 7:21:16 AM
model
"anthropic/claude-sonnet-5-20260630"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2432
moderation_latency
(null)
generation_time
10285
tokens_prompt
77
tokens_completion
356
native_tokens_prompt
93
native_tokens_completion
488
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
0.005066
router
(null)
provider_responses
0
endpoint_id
"37b16f45-eeae-45f3-9b85-2137f7c6d61b"
id
"msg_01NaVBNABo5gnGAXa7MUhovU"
is_byok
false
latency
2407
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-1782890477-5oAcyykt3BkPitpMbImD"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1782890477-MWQ7tTNG5nrXmttv5jFH"
upstream_id
"msg_01NaVBNABo5gnGAXa7MUhovU"
total_cost
0.005066
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
86.38%
Matches word count
n/a
neededClean
false
words
211
0.00%
Dialogue to Total Word Ratio
Ratio: 54.93%, Deviation: 44.93%
neededClean
false
wordsTotal
213
wordsDialogue
117
43.1902%