NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0G1QECGZCZJ8ZWTH62QWBG
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
7.0s
Cost:
$0.011315
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
86.38%
Matches word count
(details)
84.79%
Dialogue to Total Word Ratio
(details)
85.5864%
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, weighing down the corners with ketchup bottles and a half-eaten pickle. The floor plan of the Wigglesworth residence looked less like a fortress and more like a bouncy castle rental gone wrong. She circled the backyard in red Sharpie, tapping the inflatable unicorn that served as the primary obstacle. Bill slurped his milkshake, squinting at the guest list. Forty-two children. Three clowns. One magician of questionable reputation. The loot, according to their inside source—a disgruntled piñata vendor—included the new Nintendo, a remote-controlled drone, and a suspiciously expensive American Girl doll with real pearl earrings. Amateur hour, he thought, cracking his knuckles over a basket of onion rings. "We go in dressed as balloon animals," Molly whispered. Bill choked on his shake, dabbing chocolate from his beard with a crumpled napkin. He sketched escape routes through the petting zoo, noting the goat's suspicious side-eye from last week's reconnaissance. They would time their exit with the piñata break, vanishing into the confetti chaos like phantoms with oversized gift bags. The cake, Molly decided, was collateral. The presents, however, were destiny.
created_at
"2026-04-24T19:39:12.72Z"
4/24/2026, 7:39:12 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1087
moderation_latency
(null)
generation_time
6910
tokens_prompt
77
tokens_completion
317
native_tokens_prompt
98
native_tokens_completion
433
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
0.011315
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"d07b5424-eebf-4580-be20-9848d0b3e266"
is_byok
false
latency
1087
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-1777059552-wFIInzboVYvREhsNOHQc"
session_id
(null)
api_type
"completions"
id
"gen-1777059552-GOolLKQL9NovgeeR6Dmx"
upstream_id
"d07b5424-eebf-4580-be20-9848d0b3e266"
total_cost
0.011315
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
86.38%
Matches word count
n/a
neededClean
false
words
189
84.79%
Dialogue to Total Word Ratio
Ratio: 3.63%, Deviation: 6.37%
neededClean
false
wordsTotal
193
wordsDialogue
7
85.5864%