NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPTKHY1YAC1RMJKXJP7RSP
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
11.1s
Cost:
$0.012715
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
65.34%
Dialogue to Total Word Ratio
(details)
82.0256%
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
"So we walk in dressed as clowns," said Bill. "We walk in dressed as clowns." "Nobody questions a clown at a birthday party, Molly." "Everybody questions a clown. Clowns are the most questioned people in Britain." "Name one person who's questioned a clown." "My aunt Deborah. She had a clown arrested in 1998." "For what?" "Being a clown, mostly. Look, we go in as caterers. Nobody looks twice at a woman holding a tray." "I don't want to hold a tray." "You'll hold a tray, Bill, and you'll like it." "And then what? We just stroll out with forty presents under our arms?" "We take the bin bags. Every party has bin bags. Nobody stops a person carrying rubbish." "That's actually not stupid." "Thank you." "It's mildly stupid. It's the good kind of stupid." "The presents go in the bags, the bags go in the van, the van goes to Uncle Ray's lock-up." "Ray's dead, Molly." "Ray's lock-up isn't." "And if a child sees us?" "Children are unreliable witnesses. Everyone knows that." "That's a horrible thing to say." "It's a factual thing to say." "It's both," said Bill. "Fine. But I'm wearing the clown nose." "Wear the nose." "Under the caterer's hat." "Bill." "It's for luck."
created_at
"2026-07-25T13:18:25.349Z"
7/25/2026, 1:18:25 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2597
moderation_latency
(null)
generation_time
11038
tokens_prompt
75
tokens_completion
314
native_tokens_prompt
93
native_tokens_completion
490
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
0.012715
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqmFH4VFwrKGeGrdhma"
is_byok
false
latency
2597
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-1784985505-IfxkiQj9XR2z0ECIxBTN"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985505-4YbBQBpjSFpi17u6PquM"
upstream_id
"msg_011CdNqmFH4VFwrKGeGrdhma"
total_cost
0.012715
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
65.34%
Dialogue to Total Word Ratio
Ratio: 98.08%, Deviation: 8.08%
neededClean
false
wordsTotal
208
wordsDialogue
204
82.0256%