NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCRN1G5HQZ0MKVQEVVF9P4C
Run Details
Model:
Claude Opus 5 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
49.2s
Cost:
$0.124875
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
88.89%
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 cold rain had been falling on Ashcombe since Tuesday, and by Friday morning the river had swallowed the footbridge. Inspector Halloran arrived at half past six, coat collar up, a dead cigarette forgotten between the fingers of his glove. The body lay face down in the reeds below the mill, with one shoe missing and the other absurdly polished. Sergeant Pike held the umbrella over them both and said nothing, which Halloran counted among the man's very finest qualities. She was young, perhaps thirty, and someone had taken great care to arrange her hair before the river water came. Halloran crouched down and studied the pale band where a ring had very recently been worn, then looked at Pike. Someone reported this before dawn, from the telephone box outside the church, and refused to give his name at all. "A village of four hundred souls," Pike said quietly, "and not a single one will admit to ever knowing her." Halloran looked up the hill toward the lit windows, counting slowly, and found there were precisely eleven of them burning. At this hour, in this weather, eleven households awake meant eleven people who already knew all about the girl's drowning.
created_at
"2026-07-25T13:50:20.173Z"
7/25/2026, 1:50:20 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4318
moderation_latency
(null)
generation_time
49081
tokens_prompt
46
tokens_completion
1115
native_tokens_prompt
60
native_tokens_completion
4983
native_tokens_completion_images
(null)
native_tokens_reasoning
822
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"
service_tier
"default"
usage
0.124875
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNtCMgiEmUfpBcHVngHP"
is_byok
false
latency
1607
model_permaslug
"anthropic/claude-opus-5-20260723"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.18.0; linux; x64))"
http_referer
(null)
request_id
"req-1784987420-jQdONf885VAS2tSo6wlC"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784987420-djSLRtJNnFJ8un2NBMJ0"
upstream_id
"msg_011CdNtCMgiEmUfpBcHVngHP"
total_cost
0.124875
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
data_region
"global"
Evaluation details
Result
Evaluator
Details
Meta Data
88.89%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
40
8
20