NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0GE2ENBC1Q2EZKN4AW16NG
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.1s
Cost:
$0.011740
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
99.87%
Dialogue to Total Word Ratio
(details)
99.8969%
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 kitchen table, weighing down the corners with half-empty coffee mugs and a suspiciously sticky juice box. The floor plan of the Hendersons' suburban colonial looked, to her practiced eye, like a vault guarded by the world's shortest and most unpredictable security force. Twelve seven-year-olds. A clown named Bobo with questionable references. One overworked mother armed with a camera and a dwindling reserve of patience. Bill paced behind her, chewing the end of a crayon he'd mistaken for a pencil. His trench coat, which had served them well at the jewelry exchange, looked catastrophically out of place next to the Pin the Tail on the Donkey poster he'd acquired for reconnaissance purposes. He tapped the patio door on the blueprint, then the gift table, then the patio door again, as though repetition might birth inspiration. "PiƱata's our distraction," Molly said. Bill nodded solemnly, as if she'd quoted scripture. The plan was elegant in its stupidity: enter through the hedge, pose as Bobo's assistants, and escape with a pillowcase stuffed full of shrink-wrapped dinosaurs, glittering tiaras, and at least one remote-controlled helicopter that Bill had already decided, privately and passionately, belonged to him.
created_at
"2026-04-24T19:45:57.208Z"
4/24/2026, 7:45:57 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
663
moderation_latency
(null)
generation_time
7044
tokens_prompt
77
tokens_completion
325
native_tokens_prompt
98
native_tokens_completion
450
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
0.01174
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"8a2a9068-68e7-4f9e-830f-a43c8c707fc8"
is_byok
false
latency
663
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-1777059957-EWQHfm7a5MYZszQWTAtl"
session_id
(null)
api_type
"completions"
id
"gen-1777059957-4LLmZcgof1f9VVZtooA8"
upstream_id
"8a2a9068-68e7-4f9e-830f-a43c8c707fc8"
total_cost
0.01174
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
99.87%
Dialogue to Total Word Ratio
Ratio: 11.88%, Deviation: 1.88%
neededClean
false
wordsTotal
202
wordsDialogue
24
99.8969%