NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0GE8KWD438TMQFT3Y2CSPS
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.4s
Cost:
$0.012365
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
60.28%
Matches word count
(details)
95.20%
Dialogue to Total Word Ratio
(details)
77.7385%
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, talk me through it." "Right. We infil through the bouncy castle at fourteen hundred hours, just as the clown begins his balloon animal routine." "Why the clown?" "Because, Molly, nobody watches the presents when a grown man is twisting a poodle." "Genius. And the cake?" "The cake is a decoy. Ignore the cake." "Bill, I am not ignoring a cake." "Molly, focus. We've got forty-six gift bags, twelve wrapped boxes, and one suspiciously large package labeled 'Tyler.'" "Tyler's getting a pony, isn't he." "I fear so." "How do we fit a pony in the Corolla?" "We don't. The pony is collateral damage." "And the parents?" "Distracted. I've hired a magician to propose to one of the moms mid-party." "Bill, that's diabolical." "Thank you." "What's our exit?" "Piñata. We slip out during the blindfolded swinging phase. Nobody suspects the piñata." "And if a kid sees us?" "You cry. Loudly. Claim you're Tyler's aunt." "I don't look like an aunt." "Molly, everyone looks like an aunt to a six-year-old." "Fair. Let's go ruin a birthday."
created_at
"2026-04-24T19:46:03.522Z"
4/24/2026, 7:46:03 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
684
moderation_latency
(null)
generation_time
7364
tokens_prompt
77
tokens_completion
317
native_tokens_prompt
98
native_tokens_completion
475
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
0.012365
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"f526db50-03de-4a23-b3dd-3c77b204592c"
is_byok
false
latency
684
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-1777059963-xDEwy7WzBePntu40rVb8"
session_id
(null)
api_type
"completions"
id
"gen-1777059963-Btm9uMEh3GiOstchIeg8"
upstream_id
"f526db50-03de-4a23-b3dd-3c77b204592c"
total_cost
0.012365
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
60.28%
Matches word count
n/a
neededClean
false
words
185
95.20%
Dialogue to Total Word Ratio
Ratio: 94.71%, Deviation: 4.71%
neededClean
false
wordsTotal
189
wordsDialogue
179
77.7385%