NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0GGJ7TCCAP0P00DMV0J9MA
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.8s
Cost:
$0.012840
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
67.81%
Dialogue to Total Word Ratio
(details)
79.1468%
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 unrolled the blueprint across the sticky diner table, pinning the corners with ketchup bottles. Bill squinted at the crayon drawing, tilting his head like a confused spaniel. "That's a unicorn, Bill. The blueprint's underneath." "Oh. Right. Thought the security was unusually whimsical." She tapped a red circle near the backyard. "PiƱata goes up at three. That's our window. Everyone's watching little Timothy swing a bat while blindfolded." "Beautiful. Chaos, candy, and a child with a weapon." "Focus. You're the clown." Bill's face collapsed. "Absolutely not. I told you, Molly, I don't do greasepaint after what happened in Tulsa." "Nobody's bringing up Tulsa." "You just brought up Tulsa." "Put on the wig, Bill." He grumbled, stuffing a rainbow afro into his jacket like contraband. Molly slid him a rubber chicken and a duffel bag shaped like a birthday cake. "We grab the presents during 'Pin the Tail.' In, out, nine minutes." "What about the parents?" "Sheet cake. Industrial quantities. They'll be comatose." Bill honked the chicken experimentally. A waitress dropped a plate. "Stop that." "Getting into character." Molly sighed, folding the unicorn. "Just don't eat the goodie bags this time."
created_at
"2026-04-24T19:47:18.912Z"
4/24/2026, 7:47:18 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
875
moderation_latency
(null)
generation_time
7749
tokens_prompt
77
tokens_completion
334
native_tokens_prompt
98
native_tokens_completion
494
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
0.01284
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"44bc9b0e-70c4-4ed9-9ff2-5cac7146e79b"
is_byok
false
latency
867
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-1777060038-cYXoCkrHylVyiCG7R49g"
session_id
(null)
api_type
"completions"
id
"gen-1777060038-v9gkKQRCncs0a0s8JliQ"
upstream_id
"44bc9b0e-70c4-4ed9-9ff2-5cac7146e79b"
total_cost
0.01284
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
190
67.81%
Dialogue to Total Word Ratio
Ratio: 57.89%, Deviation: 7.89%
neededClean
false
wordsTotal
190
wordsDialogue
110
79.1468%