NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0G8RRJKP8N3JWH9C50MJ5J
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.0s
Cost:
$0.012940
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
91.66%
Dialogue to Total Word Ratio
(details)
92.6573%
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 unrolled the blueprint across the sticky diner table. "Okay, Bill. Entry point: the bouncy castle." "The bouncy castle?" "The bouncy castle." "Molly, I'm forty-seven." "Which is why you'll blend in with the dads." "Dads don't go in bouncy castles." "Exhausted dads hiding from their wives do. Trust me." "And then what?" "Then you belly-crawl to the gift table during musical chairs." "Why musical chairs?" "Because every adult in that yard will be watching two six-year-olds fight to the death over a folding chair. It's nature's diversion." "What about the clown?" "What about the clown?" "Molly, I cannot work around a clown. You know this about me." "I know, Bill. I know." "So?" "So I bought a clown costume." "Absolutely not." "You'll be invisible." "I'll be traumatized." "You'll be rich." "How rich can we get? These are presents for a seven-year-old." "One word, Bill. Legos." "Legos?" "Resale market's insane. Retired sets go for thousands." "Thousands?" "Thousands." "And the piñata?" "What about the piñata?" "Can I hit it?" "Focus, Bill." "I just want to hit something shaped like a donkey, Molly. Is that a crime?" "Today? Yes. Many crimes. All of them."
created_at
"2026-04-24T19:43:03.447Z"
4/24/2026, 7:43:03 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
632
moderation_latency
(null)
generation_time
6893
tokens_prompt
77
tokens_completion
353
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
"420cc362-4522-4874-ae2a-6c00f9f0849f"
is_byok
false
latency
632
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-1777059783-nuV8kevTouTmgDBt9II8"
session_id
(null)
api_type
"completions"
id
"gen-1777059783-3RGpfZZntjfnwpyAlZyr"
upstream_id
"420cc362-4522-4874-ae2a-6c00f9f0849f"
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
91.66%
Dialogue to Total Word Ratio
Ratio: 95.43%, Deviation: 5.43%
neededClean
false
wordsTotal
197
wordsDialogue
188
92.6573%