NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0GFTZJH57D3ZZTDGHVM4G1
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 50% dialogue
Duration:
6.6s
Cost:
$0.012140
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
93.65%
Matches word count
(details)
65.97%
Dialogue to Total Word Ratio
(details)
79.8087%
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 abandoned pancakes. Bill leaned in, squinting through his reading glasses, which were decorated with tiny cartoon dinosaurs he refused to explain. "The bouncy castle is our weak point," Molly said, tapping the paper. "Too many witnesses. Too much bouncing." "I can bounce," Bill said defensively. "You threw your back out opening a yogurt last Tuesday." Bill adjusted his glasses. "That yogurt was sealed by the devil himself. What about the clown?" "Reginald the Magnificent. Former Navy. Do not engage." "A Navy clown?" "Do not engage, Bill." He sighed, tracing the floor plan with a crayon he'd stolen from the kids' menu. "So we go in through the ball pit, grab the presents during pin-the-tail, and exfil before cake." "Exactly. In and out. Nobody gets hurt." "What if someone offers us cake?" Molly froze. She hadn't considered this. "We accept the cake," she said solemnly. "To refuse would blow our cover." "Two slices?" "Don't push it." Bill nodded, then pointed at the corner of the blueprint. "Molly. Why is there a pony?" "That," she whispered, "is Plan B."
created_at
"2026-04-24T19:46:55.095Z"
4/24/2026, 7:46:55 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
907
moderation_latency
(null)
generation_time
6544
tokens_prompt
77
tokens_completion
317
native_tokens_prompt
98
native_tokens_completion
466
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
0.01214
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"eed77889-3fd4-4ae6-abc0-65ce67c53dfc"
is_byok
false
latency
906
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-1777060015-XkG1nKmOoGxf2Z9ycSpi"
session_id
(null)
api_type
"completions"
id
"gen-1777060015-VFx8dJYkU3aD8yA0UpMd"
upstream_id
"eed77889-3fd4-4ae6-abc0-65ce67c53dfc"
total_cost
0.01214
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
93.65%
Matches word count
n/a
neededClean
false
words
191
65.97%
Dialogue to Total Word Ratio
Ratio: 58.03%, Deviation: 8.03%
neededClean
false
wordsTotal
193
wordsDialogue
112
79.8087%