NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0G1YC1HHB3ZWWW8TP9YGKC
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.6s
Cost:
$0.011540
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
98.71%
Matches word count
(details)
86.89%
Dialogue to Total Word Ratio
(details)
92.8020%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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, pinning down the corners with ketchup bottles. Bill squinted at the crayon drawing. "This is a placemat." "It's reconnaissance, Bill. I had the birthday girl draw it while her mother was in the bathroom." "You interrogated a seven-year-old?" "I bought her pancakes. She sang like a canary." Molly tapped a lopsided square. "Bounce house here. PiƱata here. Presents stacked in the dining room under a banner that says 'Princess Tabitha.'" Bill rubbed his temples, already regretting everything. A toddler at the next booth was watching them with unsettling intensity. "We are grown adults, Molly." "We are grown adults who are broke." "There'll be parents there." "Distracted parents. Drinking boxed wine and pretending to enjoy each other." She slid a photograph across the table. "Our way in." Bill stared at the clown costume, its painted smile somehow threatening and depressed at once. "Absolutely not." "You have the face for it." "That is deeply insulting." "I've rented the van. I've bought the balloons. I've learned three magic tricks, Bill." He sighed, picked up the red rubber nose, and turned it over in his palm like a grenade.
created_at
"2026-04-24T19:39:19.816Z"
4/24/2026, 7:39:19 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
995
moderation_latency
331
generation_time
7129
tokens_prompt
77
tokens_completion
327
native_tokens_prompt
98
native_tokens_completion
442
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
0.01154
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"4f774fb2-69f4-4803-b140-35cfa5c2c54c"
is_byok
false
latency
995
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-1777059559-Cza2gFXT8LvJMYoZUdOc"
session_id
(null)
api_type
"completions"
id
"gen-1777059559-Bpdtq07DiqJMYq39ZznT"
upstream_id
"4f774fb2-69f4-4803-b140-35cfa5c2c54c"
total_cost
0.01154
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
98.71%
Matches word count
n/a
neededClean
false
words
194
86.89%
Dialogue to Total Word Ratio
Ratio: 56.12%, Deviation: 6.12%
neededClean
false
wordsTotal
196
wordsDialogue
110
92.8020%