NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0G5WAT6MKYTJCX7ARXPKEV
Run Details
Model:
Claude Opus 4.7 (Reasoning)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
6.7s
Cost:
$0.010840
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
97.63%
Matches word count
(details)
94.29%
Dialogue to Total Word Ratio
(details)
95.9596%
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 unrolled the blueprint across the sticky diner table, pinning its corners with ketchup bottles and a half-eaten waffle. The schematic showed a suburban backyard rendered in terrifying detail: bouncy castle, piƱata trajectory, the strategic placement of a folding table groaning under brightly wrapped loot. She had circled the presents in red marker, then circled the red circles, then, for reasons she could not explain, drawn a small mustache on the clown. Bill sipped his coffee and studied the diagram like a general studying a map of Normandy. The target was a seventh birthday party for one Tobias Hendershot, whose aunt, according to Molly's extensive reconnaissance, had a gambling problem and a habit of wrapping hundred-dollar bills inside Lego sets. There would be cake. There would be chaos. There would, most importantly, be a magician arriving at three, which gave them a forty-five-minute window while every adult pretended to be delighted by disappearing scarves. "We go in dressed as parents," Molly said. Bill frowned at his waffle, considering the moral weight of stealing from a child, then considering the weight of his rent. "I'll bring the minivan," he said, and stabbed the syrup.
created_at
"2026-04-24T19:41:28.799Z"
4/24/2026, 7:41:28 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1230
moderation_latency
(null)
generation_time
6642
tokens_prompt
77
tokens_completion
311
native_tokens_prompt
98
native_tokens_completion
414
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
0.01084
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"62dd20f9-95c7-48d6-ab00-903c9d8c3fd1"
is_byok
false
latency
1230
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-1777059688-3XlYatUtdTr5DjBSjZZl"
session_id
(null)
api_type
"completions"
id
"gen-1777059688-8oYNV8EQ9DMTnDf7yLa8"
upstream_id
"62dd20f9-95c7-48d6-ab00-903c9d8c3fd1"
total_cost
0.01084
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
97.63%
Matches word count
n/a
neededClean
false
words
193
94.29%
Dialogue to Total Word Ratio
Ratio: 5.08%, Deviation: 4.92%
neededClean
false
wordsTotal
197
wordsDialogue
10
95.9596%