NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0GBBMDC15MKD3FAZQKVA1Y
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.7s
Cost:
$0.011490
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.74%
Matches word count
(details)
99.94%
Dialogue to Total Word Ratio
(details)
99.8399%
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 blueprint across the folding table, anchoring its corners with juice boxes she'd liberated from a previous reconnaissance mission. The Hendersons' backyard sprawled across the page in meticulous pencil, every sprinkler head and gopher hole accounted for. Bill leaned in, chewing the end of a crazy straw he'd been using as a pointer for the last three hours, his mustache twitching with the focused intensity of a man planning the Normandy invasion rather than the theft of birthday loot from a seven-year-old named Tobias. The bouncy castle was their primary obstacle. Twelve feet of inflated polyurethane castle, staffed by a rotating crew of sugared-up kindergartners whose capacity for screaming, Molly had calculated, exceeded the decibel output of a small jet engine. Bill had suggested a diversion involving a piƱata and three pounds of confetti cannons, but Molly preferred subtlety, which in this case meant disguising themselves as the entertainment. "I refuse to be the clown again," Bill said. She slid him a red foam nose anyway. Outside, a neighbor's sprinkler hissed against the window. Molly circled the gift table in red ink, tapped it twice, and smiled the smile of a woman who had never once been invited to a birthday party.
created_at
"2026-04-24T19:44:28.305Z"
4/24/2026, 7:44:28 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1040
moderation_latency
(null)
generation_time
6614
tokens_prompt
77
tokens_completion
323
native_tokens_prompt
98
native_tokens_completion
440
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
0.01149
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"8399ab3b-dd8b-4a14-9d2e-132605645c9d"
is_byok
false
latency
840
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-1777059868-EaVEpsovB6sNDCjk959p"
session_id
(null)
api_type
"completions"
id
"gen-1777059868-D2QKZcO0fMqVMuTjnTY8"
upstream_id
"8399ab3b-dd8b-4a14-9d2e-132605645c9d"
total_cost
0.01149
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.74%
Matches word count
n/a
neededClean
false
words
204
99.94%
Dialogue to Total Word Ratio
Ratio: 11.59%, Deviation: 1.59%
neededClean
false
wordsTotal
207
wordsDialogue
24
99.8399%