NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0G57D0D4W33WRPC16A58FN
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.2s
Cost:
$0.011965
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
81.27%
Matches word count
(details)
95.20%
Dialogue to Total Word Ratio
(details)
88.2372%
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 at eleven o'clock, clown at two o'clock, piñata—dead center." "What about the kids?" "What about them?" "They're, like, everywhere, Molly. They're a swarm. They're a biblical plague in sparkle shoes." "That's why we wear the costumes." "I'm not being a clown." "You're being the clown, Bill. I already called princess." "Why do you get to be princess?" "Because I have the tiara, Bill. I have committed to the bit." "Fine. What's the extraction plan?" "Simple. You distract with balloon animals, I sweep the gift table, we meet at the minivan." "I can't make balloon animals." "Make a snake. A snake is a straight balloon, Bill. A snake is literally the balloon." "And if someone asks for a giraffe?" "Tell them the giraffe is extinct." "Giraffes aren't extinct." "They are at this party." "What about the parents?" "Drunk on boxed wine by one-fifteen. Window closes at two when the sugar crash hits." "And if we get caught?" "We cry, Bill. Loudly. Nobody arrests a sobbing princess." "That's the whole plan?" "That's the whole plan."
created_at
"2026-04-24T19:41:07.366Z"
4/24/2026, 7:41:07 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
877
moderation_latency
(null)
generation_time
6996
tokens_prompt
77
tokens_completion
322
native_tokens_prompt
98
native_tokens_completion
459
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
0.011965
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"2bec4c61-178b-42aa-9015-d6843a0ee6ea"
is_byok
false
latency
877
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-1777059667-9a7qjda53fs1mFwzg1wx"
session_id
(null)
api_type
"completions"
id
"gen-1777059667-IZchgL1WveWDAD8y8kjA"
upstream_id
"2bec4c61-178b-42aa-9015-d6843a0ee6ea"
total_cost
0.011965
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
81.27%
Matches word count
n/a
neededClean
false
words
188
95.20%
Dialogue to Total Word Ratio
Ratio: 94.71%, Deviation: 4.71%
neededClean
false
wordsTotal
189
wordsDialogue
179
88.2372%