NC Bench
Overview
About
Tests
Models
Vendors
Compare
Run: 2026-02-24-01KJ8WTYH4VAAHD2E30E6DQJ4E
Run Details
Model:
Claude Opus 4.6 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
17.6s
Cost:
$0.036905
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 10 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The old mansion stood silent against the dark winter sky. Detective Harris stepped out of her car into the rain. A single light flickered behind curtains on the third floor. Someone had called the station about a body at midnight. She pulled her coat tighter and walked toward the door. The front door was unlocked, which struck her as strange. Inside, the foyer smelled of roses and something far worse. Her flashlight beam cut through the heavy darkness like glass. A man lay crumpled at the bottom of the stairs. His eyes were open, staring at nothing but the ceiling. Blood had pooled beneath his head in a dark halo. Harris knelt beside the body and studied the man's face. She recognized him instantly and felt her stomach drop hard. It was Judge Whitmore, the most powerful man in town. This was no accident, and she already knew it well. Somewhere above her, a floorboard creaked in the empty house.
created_at
"2026-02-24T22:38:08.524Z"
2/24/2026, 10:38:08 PM
model
"anthropic/claude-4.6-opus-20260205"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1516
moderation_latency
233
generation_time
17166
tokens_prompt
46
tokens_completion
645
native_tokens_prompt
61
native_tokens_completion
1464
native_tokens_completion_images
(null)
native_tokens_reasoning
405
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.036905
router
(null)
provider_responses
0
endpoint_id
"a8708fb9-08ea-43bb-a3b1-165c87ef09df"
id
"886ada77-db5b-4537-9ca5-15e21df54a3f"
is_byok
false
latency
1447
model_permaslug
"anthropic/claude-4.6-opus-20260205"
provider_name
"Amazon Bedrock"
status
200
api_type
"completions"
id
"gen-1771972688-gDz6Eivv5YPh9IOuC5k5"
upstream_id
"886ada77-db5b-4537-9ca5-15e21df54a3f"
total_cost
0.036905
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
sentences
16
wordCounts
0
10
1
10
2
10
3
10
4
10
5
10
6
10
7
10
8
10
9
10
10
10
11
10
12
10
13
10
14
10
15
10