NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPQ4DEAE75C6A8RKER9G2F
Run Details
Model:
Claude Opus 5
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
10.9s
Cost:
$0.013565
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
77.39%
Dialogue to Total Word Ratio
(details)
88.5666%
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're clear," Molly said. "Bouncy castle at the rear, cake table by the patio doors." "And the presents?" "Living room. Stacked like a shrine." "How many kids?" "Eleven. Twelve if Dorian's cousin recovers from the chickenpox." "Eleven kids," Bill said. "Molly, I've done armored cars. I've done a diamond exchange in Antwerp. I have never done eleven eight-year-olds." "They're distracted. There's a magician." "A magician?" "Local man. Calls himself the Astonishing Reginald." "Is he astonishing?" "He pulls a rabbit out of a bag he keeps the rabbit in." "So we've got, what, four minutes of pigeon-based cover?" "Six. He does a long thing with a rope." Bill exhaled. "And the parents?" "Kitchen. Prosecco. They stop counting children at glass two." "What am I wearing?" "Nothing suspicious. Cargo shorts. Sun hat. Look like an uncle." "I don't look like an uncle." "Bill, you look like every uncle. You look like the concept of uncle." "And you?" "Face paint. I'm doing butterflies." "You can't paint." "I can paint a butterfly on a child." "Then we're in and out with, what, thirty parcels?" "Thirty-one. And Bill?" "Yes?" "If a girl called Priya offers you a sausage roll, take it. She's the only one who's onto us."
created_at
"2026-07-25T13:16:31.541Z"
7/25/2026, 1:16:31 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1569
moderation_latency
(null)
generation_time
10830
tokens_prompt
75
tokens_completion
326
native_tokens_prompt
93
native_tokens_completion
524
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
0.013565
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqcofii6rtE1zaHRbXX"
is_byok
false
latency
1559
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-1784985391-INHObmnSWjQJlb2pkYk1"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985391-060APMzqrJBvOzR24RB7"
upstream_id
"msg_011CdNqcofii6rtE1zaHRbXX"
total_cost
0.013565
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
99.74%
Matches word count
n/a
neededClean
false
words
204
77.39%
Dialogue to Total Word Ratio
Ratio: 97.12%, Deviation: 7.12%
neededClean
false
wordsTotal
208
wordsDialogue
202
88.5666%