NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0GA8KVP6PZY2HYD431CQQD
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.0s
Cost:
$0.011715
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
75.16%
Matches word count
(details)
32.20%
Dialogue to Total Word Ratio
(details)
53.6785%
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, flattening them with a ketchup bottle and a bowl of creamers. "Entry point is the bouncy castle," she said, tapping the page. "Structural weakness, northeast corner." Bill squinted. "You want us to infiltrate through an inflatable?" "I want us to commando-roll through an inflatable. There's a difference." "And the guests?" "Seventeen hostiles, average height four feet, armed with juice boxes." Bill whistled low and stirred his coffee. "What about the mom?" "Brenda. Ex-PTA president. Do not engage." "Copy that." He leaned back, chewing a toothpick like it owed him money. "And the loot?" "Presents stack near the piƱata. We grab, we bag, we exfil through the garage before the cake hits the table." "What if they sing 'Happy Birthday' early?" "Then we improvise. You harmonize on the low end." Bill nodded solemnly, as though she'd asked him to defuse a bomb. He tapped the blueprint where someone had drawn a smiling unicorn in red crayon. "Molly." "What." "This is a placemat from Chuck E. Cheese." She didn't look up. "Reconnaissance, William. I've been inside. I know the terrain."
created_at
"2026-04-24T19:43:52.448Z"
4/24/2026, 7:43:52 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
686
moderation_latency
(null)
generation_time
6893
tokens_prompt
77
tokens_completion
316
native_tokens_prompt
98
native_tokens_completion
449
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
0.011715
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"ac3809b5-0e4d-433c-b9fa-67bc8faf71ba"
is_byok
false
latency
686
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-1777059832-CGVqyo46bLwMozV9KTxC"
session_id
(null)
api_type
"completions"
id
"gen-1777059832-P0tWpwXRhkwEMjOWoR5Q"
upstream_id
"ac3809b5-0e4d-433c-b9fa-67bc8faf71ba"
total_cost
0.011715
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
75.16%
Matches word count
n/a
neededClean
false
words
187
32.20%
Dialogue to Total Word Ratio
Ratio: 60.32%, Deviation: 10.32%
neededClean
false
wordsTotal
189
wordsDialogue
114
53.6785%