NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPPYF00RZHM9H0AN701S8A
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.5s
Cost:
$0.013340
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
51.23%
Dialogue to Total Word Ratio
(details)
74.9737%
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
"The clown," Molly said. "That's the weak point." "Clowns are never the weak point. Clowns are the strongest point. Clowns have knives in their little cars." "Bill." "I'm just saying I've met clowns." "The clown arrives at two. We arrive at one-fifty. We are the clown." "Both of us? One clown, two men?" "You're the balloon assistant." "There's no such thing as a balloon assistant." "Nobody at a seven-year-old's birthday party knows the industry standard for balloon assistants, Bill." "Somebody's mother will. Somebody's mother always knows." "Then you distract her." "With what?" "Balloons." "I can't do balloons. My hands sweat. They pop." "Then do a sad face and say the balloons were stolen. Mothers love a tragedy." "And the presents?" "Pile by the window, always. Every party, always the window, always unguarded, because nobody in this country believes anyone would rob a child." "Because it's despicable." "Because it's easy." "Both, Molly. It can be both." "Sixty presents. Average value, thirty quid." "That's eighteen hundred." "That's a holiday." "That's a jail sentence with a very specific description." "Bring the sack." "We're stealing from a child." "We're stealing from a child's *aunts*, Bill. Aunts buy rubbish. We're doing him a kindness." "...What's my clown name?" "Sweaty." "Right. Fine."
created_at
"2026-07-25T13:16:25.448Z"
7/25/2026, 1:16:25 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1554
moderation_latency
174
generation_time
11225
tokens_prompt
75
tokens_completion
351
native_tokens_prompt
93
native_tokens_completion
515
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
0.01334
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqcN27r4HGRC6FwozSh"
is_byok
false
latency
1551
model_permaslug
"anthropic/claude-opus-5-20260723"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784985385-BoXOvpJIK4MXiYEkc8n7"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985385-Ajd3lbodJXHxhPTs43sA"
upstream_id
"msg_011CdNqcN27r4HGRC6FwozSh"
total_cost
0.01334
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
206
51.23%
Dialogue to Total Word Ratio
Ratio: 99.04%, Deviation: 9.04%
neededClean
false
wordsTotal
209
wordsDialogue
207
74.9737%