NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0G1FW7VJTYHCYBNHTWNQY5
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 90% dialogue
Duration:
7.4s
Cost:
$0.013315
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
99.38%
Matches word count
(details)
94.41%
Dialogue to Total Word Ratio
(details)
96.8921%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 90% 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 crouched behind the hedge, binoculars pressed to her face. "Bill, we've got a clown at twelve o'clock." "Armed?" "With balloons." "Balloon animals can be weaponized, Molly. I saw a documentary." "You watched *It* again, didn't you?" "That's not the point. What's the perimeter looking like?" "Bouncy castle to the east, piñata to the west, and a sheet cake the size of a Buick." "And the presents?" "Stacked on a picnic table. Bill, there's a *mountain* of them." "How many kids?" "Twelve. Maybe fifteen. One of them is crying already." "Perfect. Chaos is our friend. What's the birthday boy situation?" "Girl. She's turning seven. Princess theme. I'm wearing the tiara for cover." "Molly, you're forty-three." "I have a youthful glow." "You have a parole officer." "Focus, Bill. Here's the plan: I distract the parents with a fake allergic reaction near the hummus—" "Why hummus?" "Parents fear hummus. It's chunky. Then you sweep in dressed as Uncle Gary." "Who's Uncle Gary?" "Everyone has an Uncle Gary. Nobody questions Uncle Gary." "And the getaway?" "Minivan. I already put a car seat in the back for authenticity." "Molly, you're a genius." "I know. Now grab the juice boxes."
created_at
"2026-04-24T19:39:04.971Z"
4/24/2026, 7:39:04 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
898
moderation_latency
(null)
generation_time
7357
tokens_prompt
77
tokens_completion
343
native_tokens_prompt
98
native_tokens_completion
513
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
0.013315
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"2a92fe9c-169f-4934-8773-7a4822e92231"
is_byok
false
latency
894
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-1777059544-IKdcrZKN1XXRlwFRXchb"
session_id
(null)
api_type
"completions"
id
"gen-1777059544-WIXDAN1uROkHPht4fq83"
upstream_id
"2a92fe9c-169f-4934-8773-7a4822e92231"
total_cost
0.013315
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
94.41%
Dialogue to Total Word Ratio
Ratio: 94.90%, Deviation: 4.90%
neededClean
false
wordsTotal
196
wordsDialogue
186
96.8921%