NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZV6VM446Z7VFRH3BX0YVXD
Run Details
Model:
Claude Opus 4.7
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.1s
Cost:
$0.010490
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
66.94%
Dialogue to Total Word Ratio
(details)
82.2861%
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
Molly spread the blueprints across the sticky diner table, smoothing them with the side of her hand. The paper was covered in juice box rings and a suspicious smear of what appeared to be frosting, which was either reconnaissance or a terrible omen. Bill, hunched over his coffee like a gargoyle nursing a grudge, studied the layout of the Pemberton residence with the grim intensity of a man who had been outsmarted by a bounce house once and never recovered. The party, according to their intel, would feature seventeen six-year-olds, a magician of questionable licensing, and approximately forty-two wrapped presents stacked in the sunroom like a glittering Everest of capitalism. Molly had already mapped three exits, two blind spots, and the precise location of the piƱata, which she'd flagged as a potential weapon. Bill had dressed for the occasion in a clown costume he'd bought online, though the ruffled collar was, in his professional opinion, an affront to dignity. "I hate children," Bill muttered. "Focus," Molly said. He pointed to the cake. She nodded. They had forty minutes until showtime, a duffel bag full of balloons, and absolutely no moral compass between them.
created_at
"2026-04-24T13:35:00.753Z"
4/24/2026, 1:35:00 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
643
moderation_latency
(null)
generation_time
7043
tokens_prompt
77
tokens_completion
304
native_tokens_prompt
98
native_tokens_completion
400
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
0.01049
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"07434d13-4340-481d-9d87-d6bcb5fe3604"
is_byok
false
latency
642
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-1777037700-el9gLI8G6LWNA5ht2WLp"
session_id
(null)
api_type
"completions"
id
"gen-1777037700-Wt8xiifdgo3IVwQuB9E6"
upstream_id
"07434d13-4340-481d-9d87-d6bcb5fe3604"
total_cost
0.01049
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
193
66.94%
Dialogue to Total Word Ratio
Ratio: 2.04%, Deviation: 7.96%
neededClean
false
wordsTotal
196
wordsDialogue
4
82.2861%