NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0G7VTS9GD6F0Q8R0EWGAM4
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.8s
Cost:
$0.011515
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
66.53%
Dialogue to Total Word Ratio
(details)
82.9525%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% 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 spread the blueprints across the sticky diner table, anchoring the corners with ketchup bottles and a half-eaten stack of pancakes. The Henderson residence glowed on the page in surgical blue ink, every doorway and air vent catalogued with the obsessive precision of a woman who had spent three weeks pretending to be a birthday clown's assistant. Bill slurped his coffee and squinted at the floor plan, his enormous mustache quivering with the weight of his concentration. Seven-year-old Timmy Henderson was turning eight on Saturday, and by all reliable intelligence, his grandmother, a retired oil heiress with more money than judgment, had purchased him approximately forty-seven wrapped gifts, including what the neighborhood gossip insisted was a solid gold rocking horse. "Bouncy castle's the distraction," Molly said. Bill nodded, tracing a finger along the backyard perimeter toward the gift table, which sat beneath a piñata shaped like a disturbingly cheerful llama. Their plan required two clown costumes, a stolen magician's van, and a willingness to sprint from children, which Bill possessed in abundance. Molly tapped the piñata with her pen, smiling the small dangerous smile of a woman about to ruin a child's entire Saturday afternoon.
created_at
"2026-04-24T19:42:33.823Z"
4/24/2026, 7:42:33 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
893
moderation_latency
210
generation_time
6486
tokens_prompt
77
tokens_completion
320
native_tokens_prompt
98
native_tokens_completion
441
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
0.011515
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"dd5e9029-faa8-4900-81a1-d8d9c2fbd4c9"
is_byok
false
latency
892
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-1777059753-ngnXbpWhIGwDVhuuGkOV"
session_id
(null)
api_type
"completions"
id
"gen-1777059753-90QzVpRqgbuvt3M1qBN0"
upstream_id
"dd5e9029-faa8-4900-81a1-d8d9c2fbd4c9"
total_cost
0.011515
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.38%
Matches word count
n/a
neededClean
false
words
195
66.53%
Dialogue to Total Word Ratio
Ratio: 2.01%, Deviation: 7.99%
neededClean
false
wordsTotal
199
wordsDialogue
4
82.9525%