NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0G94SJPVARG512DMDAPZWJ
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
10.0s
Cost:
$0.013190
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
0.65%
Dialogue to Total Word Ratio
(details)
50.0160%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 50% 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, nudging aside a plate of congealing hash browns. The crayon drawing depicted a suburban backyard with alarming detail, including a bounce house labeled "FORTRESS." "The target is a seven-year-old named Tyler," she said. "His mother posted the guest list on Facebook. Twelve kids, three parents, one clown." Bill paled. "A clown?" "Focus, Bill." "I don't do clowns. You know I don't do clowns." "It's a children's party, not a horror movie." She tapped the blueprint. "Presents accumulate on this table here, between the veggie platter and the juice boxes. We go in at piñata o'clock." "Piñata o'clock?" "Maximum chaos. Candy everywhere, kids screaming, parents filming. Nobody's watching the loot." Bill chewed his pencil thoughtfully. "What's our cover?" "You're Uncle Gary. I'm your wife, Denise. We're distant relatives nobody remembers inviting." "Why am I always Uncle Gary?" "Because you have Uncle Gary energy." He considered this, then nodded solemnly. "Fair." He pointed at a squiggle on the blueprint. "What's that?" "Golden retriever. Name's Biscuit. Friendly, but she'll bark at strangers." "So we bring bacon." "We bring bacon," Molly agreed, and shook his hand across the hash browns.
created_at
"2026-04-24T19:43:15.765Z"
4/24/2026, 7:43:15 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3464
moderation_latency
197
generation_time
9795
tokens_prompt
77
tokens_completion
342
native_tokens_prompt
98
native_tokens_completion
508
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
0.01319
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"6c6778ab-6e19-4acd-93cf-ed21faa3c08b"
is_byok
false
latency
3464
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-1777059795-3qZl0cDViZIu9wtgAPS1"
session_id
(null)
api_type
"completions"
id
"gen-1777059795-CWvO8VfDrPFnXcChP3Af"
upstream_id
"6c6778ab-6e19-4acd-93cf-ed21faa3c08b"
total_cost
0.01319
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
0.65%
Dialogue to Total Word Ratio
Ratio: 64.97%, Deviation: 14.97%
neededClean
false
wordsTotal
197
wordsDialogue
128
50.0160%