NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZV7C7NTN7617V34THCS35F
Run Details
Model:
Claude Opus 4.7
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.8s
Cost:
$0.010915
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
90.48%
Matches word count
(details)
94.86%
Dialogue to Total Word Ratio
(details)
92.6743%
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 folding card table, weighing down the corners with half-eaten juice boxes she'd swiped from a reconnaissance mission three days prior. The floor plan of the Pemberton residence sprawled before them in loving detail: the bouncy castle in the backyard, the piƱata suspended from the old oak, and, most critically, the mountain of gift-wrapped boxes piled high on the sunroom table. Bill adjusted his clown wig and studied his reflection in the toaster. The red nose kept slipping. He looked, he thought, like a man who had made several questionable career decisions in rapid succession, which was accurate. "The magician arrives at two," Molly said, tapping the blueprint. Bill grunted, stuffing balloons into his oversized pockets. The plan was elegant in its stupidity. They would blend in with the entertainment, wait for cake time when every child's attention turned toward sugar, then load the presents into a trick suitcase and waddle out whistling. Nobody suspected clowns. Nobody ever suspected clowns, which Bill had always found suspicious in itself. Molly circled the sunroom in red marker. "Remember, no eating the cake." Bill's silence was extremely unconvincing.
created_at
"2026-04-24T13:35:17.763Z"
4/24/2026, 1:35:17 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
652
moderation_latency
(null)
generation_time
6695
tokens_prompt
77
tokens_completion
315
native_tokens_prompt
98
native_tokens_completion
417
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
0.010915
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"2432caa5-9fc7-4a74-ab98-fbff626e3771"
is_byok
false
latency
652
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-1777037717-GQ6bEy7ExX1sAFQgRv1O"
session_id
(null)
api_type
"completions"
id
"gen-1777037717-qOWmeKc7mf1HeFCUMfVh"
upstream_id
"2432caa5-9fc7-4a74-ab98-fbff626e3771"
total_cost
0.010915
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
90.48%
Matches word count
n/a
neededClean
false
words
190
94.86%
Dialogue to Total Word Ratio
Ratio: 5.21%, Deviation: 4.79%
neededClean
false
wordsTotal
192
wordsDialogue
10
92.6743%