NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0GB0755M806QH2ZV3CAXTW
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.3s
Cost:
$0.012015
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
59.12%
Dialogue to Total Word Ratio
(details)
79.2466%
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 unrolled the blueprints across the sticky diner table, weighting the corners with ketchup bottles and a half-eaten plate of hash browns. The floor plan of the Tumblebee Play Palace sprawled before them, annotated in purple crayon because she'd run out of pens and refused to buy more on principle. Bill squinted at the ball pit, which she had circled ominously and labeled "DANGER ZONE." He leaned back, chewing a toothpick with the solemnity of a man contemplating war. Six-year-old Timothy Pemberton's birthday extravaganza was, by all reliable intelligence, going to be the loot score of the decade. Forty-two children. Forty-two sets of grandparents competing for favorite-grandparent status. Rumor had it the kid was getting a gold-plated scooter, though Molly suspected that was a plant. "Clowns," Bill muttered, tapping the east entrance. Molly nodded gravely. Clowns complicated everything. She'd already secured the disguises: two enormous bumblebee costumes rented under a fake name from a theatrical supply shop run by a nearsighted Lithuanian. The plan was elegant in its stupidity. They would waddle in, mingle near the piƱata, and exfiltrate through the emergency exit beside the bouncy castle, dragging duffel bags stuffed with other people's joy.
created_at
"2026-04-24T19:44:16.617Z"
4/24/2026, 7:44:16 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
878
moderation_latency
(null)
generation_time
7275
tokens_prompt
77
tokens_completion
325
native_tokens_prompt
98
native_tokens_completion
461
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
0.012015
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"39089b7c-4f93-4903-a67f-01e9fb182fe4"
is_byok
false
latency
878
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-1777059856-3iOU8oJA6slzvNzVL9Nz"
session_id
(null)
api_type
"completions"
id
"gen-1777059856-MNt6EDZBgKPLMGwDT9uv"
upstream_id
"39089b7c-4f93-4903-a67f-01e9fb182fe4"
total_cost
0.012015
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
59.12%
Dialogue to Total Word Ratio
Ratio: 1.49%, Deviation: 8.51%
neededClean
false
wordsTotal
202
wordsDialogue
3
79.2466%