NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KPZTWJAQ413P9Z2VNGX0P8Q2
Run Details
Model:
Claude Opus 4.7
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
5.4s
Cost:
$0.010275
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
82.51%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 20 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
Rain hammered against the tall Victorian windows of Thornfield Manor as Detective Sarah Chen stepped through the grand oak doorway. The butler, pale and trembling, gestured silently toward the library where something terrible had clearly taken place that evening. Seven guests huddled together in the adjacent drawing room, their faces drawn tight with fear and barely concealed suspicion. Lord Ashworth lay sprawled across the Persian rug, a silver letter opener buried deep within his broad, still chest. Candles flickered wildly on the mantelpiece, casting dancing shadows that seemed to mock the gruesome scene unfolding before her experienced eyes. Sarah knelt carefully beside the body, noting the absence of blood pooling beneath the expensive black dinner jacket he wore. Someone had moved him here, she realized immediately, her sharp gaze sweeping across the room for telltale signs of disturbance. A single muddy footprint marked the polished floor near the window, which stood slightly ajar despite the howling storm outside. Behind her, the grandfather clock struck midnight with twelve deep, resonant tones that echoed hauntingly through the silent, watchful house.
created_at
"2026-04-24T13:29:23.556Z"
4/24/2026, 1:29:23 PM
model
"anthropic/claude-4.7-opus-20260416"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
864
moderation_latency
(null)
generation_time
5279
tokens_prompt
46
tokens_completion
295
native_tokens_prompt
65
native_tokens_completion
398
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
0.010275
router
(null)
provider_responses
0
endpoint_id
"0fa65117-00d9-4835-808d-9b68041d9ce4"
id
"c84f62be-3bc2-4f77-9806-8d8a3b20c587"
is_byok
false
latency
864
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-1777037363-0ILfb9SIhHczaqNL8fgU"
session_id
(null)
api_type
"completions"
id
"gen-1777037363-nsZaCmIgiZb2ny387KhO"
upstream_id
"c84f62be-3bc2-4f77-9806-8d8a3b20c587"
total_cost
0.010275
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
82.51%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
20
1
19
2
19
3
19
4
21
5
20
6
20
7
20
8
20