NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-02-24-01JMWZR8EFMFZ21CRQ9FCDXX9H
Run Details
Model:
Claude 3.7 Sonnet
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
4.2s
Cost:
$0.003462
Provider:
Anthropic
Evaluation summary
Score
Evaluator
Details Link
58.71%
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
The rain pounded relentlessly on the old mansion's roof while thunder crashed across the sky like angry celestial drums. Detective Sarah Morgan stared at the lifeless body sprawled across the antique Persian rug in the grand library. Blood had seeped into the expensive fabric, creating a dark halo around the victim's head where the bullet entered. The household staff huddled near the doorway, their faces pale with shock as they whispered among themselves fearfully. A crystal tumbler lay shattered beside an overturned chair, whiskey mingling with blood in a macabre cocktail on the floor. Sarah noticed the victim's hand was clutching something tightly, a small object that glinted gold in the dim lighting. "Nobody leaves this room," she commanded, her voice cutting through the tension as she pulled on latex examination gloves. The grandfather clock in the corner struck midnight, each resonant chime seeming to echo the finality of Lord Blackwood's death.
id
"gen-1740434580-uqerkXTUGryDtOCIAXAD"
upstream_id
"msg_011PDr6BBLTenE6RWHW6dxYV"
total_cost
0.003462
cache_discount
(null)
provider_name
"Anthropic"
created_at
"2025-02-24T22:03:04.624311+00:00"
2/24/2025, 10:03:04 PM
model
"anthropic/claude-3-7-sonnet-20250219:beta"
app_id
182717
streamed
true
cancelled
false
latency
490
moderation_latency
(null)
generation_time
3603
tokens_prompt
42
tokens_completion
189
native_tokens_prompt
44
native_tokens_completion
222
native_tokens_reasoning
0
num_media_prompt
(null)
num_media_completion
(null)
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.003462
Evaluation details
Result
Evaluator
Details
Meta Data
58.71%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
19
1
18
2
19
3
18
4
20
5
19
6
19
7
20