NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0G2K4ZY3QF3VHYVZ0C2097
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
6.8s
Cost:
$0.012940
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
94.18%
Dialogue to Total Word Ratio
(details)
93.9124%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 unfolded the blueprint across the hood of the van. "Okay, Bill. Bouncy castle's here, piƱata's here, and the present table is right next to the clown." "I hate clowns." "Everyone hates clowns. That's why it's the perfect distraction." "What's our exit?" "Back gate, through the petting zoo, over the fence by the porta-potty." "There's a petting zoo?" "Bill, focus." "I'm just saying, goats are unpredictable." "More unpredictable than a bounce house full of sugar-drunk seven-year-olds?" "Fair point." "You'll go in dressed as Uncle Terry. Nobody's met Uncle Terry. Uncle Terry lives in Saskatchewan." "And you?" "Face painter. Nobody questions a face painter." "Molly, you can't draw." "I can draw a butterfly." "You cannot draw a butterfly." "I can draw something that a four-year-old will accept as a butterfly under duress." "What about the parents?" "Open bar, Bill. Open bar at a kid's party means those parents will be face-down in the guacamole by two." "And the presents?" "Straight into the diaper bag. Nobody checks a diaper bag." "Molly, this might be our masterpiece." "Bill, this is the Ocean's Eleven of birthday parties." "What's the theme?" "Paw Patrol." "God help us."
created_at
"2026-04-24T19:39:41.096Z"
4/24/2026, 7:39:41 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
901
moderation_latency
(null)
generation_time
6706
tokens_prompt
77
tokens_completion
345
native_tokens_prompt
98
native_tokens_completion
498
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
0.01294
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"78e38362-a407-4dbf-a761-b72d321ddb20"
is_byok
false
latency
898
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-1777059581-eT8nwt33dHC1wG9VMxJB"
session_id
(null)
api_type
"completions"
id
"gen-1777059581-MDvHtuLW4VdKrjx4EsfN"
upstream_id
"78e38362-a407-4dbf-a761-b72d321ddb20"
total_cost
0.01294
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
191
94.18%
Dialogue to Total Word Ratio
Ratio: 94.95%, Deviation: 4.95%
neededClean
false
wordsTotal
198
wordsDialogue
188
93.9124%