NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZV3FEW5P4NP1X6XCC0JRM8
Run Details
Model:
Claude Opus 4.7
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.9s
Cost:
$0.012065
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
68.10%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
52.4451%
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
"Molly, we are not stealing from a six-year-old." "We're stealing from a six-year-old's *guests*, Bill. Totally different crime." "Oh, well, when you put it that way—no, it's still terrible." "The invitation said 'no gifts over fifty dollars.' Do you know what that means?" "That the parents are reasonable?" "It means at least twenty kids showing up with fifty-dollar presents. That's a grand. In wrapping paper. Sitting on a folding table. Next to a sheet cake." "There's going to be a clown, Molly." "Clowns are a distraction. We use the clown." "I'm not 'using' a clown." "Fine. You be the clown." "Absolutely not." "Bill, you already own the shoes." "Those are orthopedic!" "Exactly. Built-in disguise." "What's our exit strategy? A bounce house?" "Funny you should say that." "Molly." "The bounce house deflates in forty seconds. We roll it up, presents inside, walk out like party rental guys." "And the birthday boy?" "Gets the gift of resilience. Priceless, really. We're doing him a favor." "You are a monster." "I'm a professional." "Fine. But I'm not honking a nose." "You'll honk the nose, Bill." "...I'll honk the nose."
created_at
"2026-04-24T13:33:09.993Z"
4/24/2026, 1:33:09 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
988
moderation_latency
(null)
generation_time
7832
tokens_prompt
77
tokens_completion
327
native_tokens_prompt
98
native_tokens_completion
463
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"
usage
0.012065
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"72a96b5c-c20f-4704-b271-c7616a40a7e1"
is_byok
false
latency
988
model_permaslug
"anthropic/claude-4.7-opus-20260416"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777037589-ls4tRSeBUCvguLIG0ggC"
session_id
(null)
api_type
"completions"
id
"gen-1777037589-twAggvCHwZfSQ8NHHCWq"
upstream_id
"72a96b5c-c20f-4704-b271-c7616a40a7e1"
total_cost
0.012065
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
68.10%
Matches word count
n/a
neededClean
false
words
186
36.79%
Dialogue to Total Word Ratio
Ratio: 100.00%, Deviation: 10.00%
neededClean
false
wordsTotal
192
wordsDialogue
192
52.4451%