NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0G7ANC9SP946BP4AMF2SM0
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
7.7s
Cost:
$0.012490
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
0.06%
Dialogue to Total Word Ratio
(details)
49.9897%
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 unrolled the blueprint across the sticky diner table, pinning the corners with ketchup bottles. Bill squinted at the crayon scribbles, which appeared to depict a bouncy castle, a clown, and something that was either a piƱata or a hanged man. "This is the floor plan?" Bill asked. "Drew it from memory. I cased the joint Tuesday." "Molly, you were invited. Your nephew turns seven." "Recon is recon," she said. "Now focus. The presents pile up here, by the cake table. We hit during 'Pin the Tail on the Donkey.' Blindfolds mean witnesses are useless." "What about the parents?" "Sugar-crashed and scrolling. We'll be ghosts." Bill tapped a suspicious red blob. "And this?" "Magician. Goes on at three. He's the wild card." "A magician is the wild card?" "Bill, the man makes rabbits disappear. He's a professional thief with better PR." Bill rubbed his temples. "We're stealing from children." "We're stealing from a demographic that can't identify us in a lineup. There's a difference." "There really isn't." "Bill." Molly grabbed his hand, tender and grave. "Do you know what a seven-year-old gets these days? iPads. Drones. Actual cryptocurrency. My nephew got Bitcoin." Bill picked up the crayon.
created_at
"2026-04-24T19:42:16.243Z"
4/24/2026, 7:42:16 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1001
moderation_latency
(null)
generation_time
7661
tokens_prompt
77
tokens_completion
329
native_tokens_prompt
98
native_tokens_completion
480
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
0.01249
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"080069f8-9373-46b0-a818-cc82a5b8f980"
is_byok
false
latency
917
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-1777059736-syWODyDRXObaA9FHQGg5"
session_id
(null)
api_type
"completions"
id
"gen-1777059736-NLe4Lvu8k9IKh9Dwxflx"
upstream_id
"080069f8-9373-46b0-a818-cc82a5b8f980"
total_cost
0.01249
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
197
0.06%
Dialogue to Total Word Ratio
Ratio: 66.50%, Deviation: 16.50%
neededClean
false
wordsTotal
200
wordsDialogue
133
49.9897%