NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-07-25-01KYCPSCPQWWEC7AWXPJYYBP48
Run Details
Model:
Claude Opus 5
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
9.3s
Cost:
$0.009750
Provider:
Amazon Bedrock
Evaluation summary
Score
Evaluator
Details Link
76.39%
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 arrived at midnight, hammering the slate roofs of Ashgrove like a thousand small fists demanding to be admitted. Inspector Nella Vance stood beneath the dripping archway of Thornfield House, counting the lit windows, and found one too many. The housekeeper who had telephoned her waited inside, wringing a dishcloth she had apparently forgotten she was still holding. "He's in the library," the woman said, and her voice cracked open on the word like ice beneath a boot heel. Nella wiped her boots on the mat, a courtesy the dead man would have appreciated, then walked down the corridor. Sir Edmund Hale sat in his leather chair with his back to the door, facing the tall black window. A chess board rested before him, the white king toppled, and a single glass of sherry stood untouched beside it. There was no blood, no wound, no disorder of any kind, only the stillness that comes after something ends. Nella crouched and studied the carpet, where damp footprints led from the window to the chair and then stopped. They did not lead back out again, which was, she thought, the first genuinely interesting fact of the night.
created_at
"2026-07-25T13:17:45.565Z"
7/25/2026, 1:17:45 PM
model
"anthropic/claude-opus-5-20260723"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1750
moderation_latency
(null)
generation_time
9191
tokens_prompt
46
tokens_completion
291
native_tokens_prompt
60
native_tokens_completion
378
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"
service_tier
"default"
usage
0.00975
router
(null)
provider_responses
0
endpoint_id
"76cb4608-f48c-483d-8da8-9957fb44244e"
id
"msg_011CdNqiFpivxnz6eDHQx4VM"
is_byok
false
latency
1750
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-1784985465-bGfrN1KurUA906JiZIDI"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1784985465-2hPM90dNgTubtypvwyXz"
upstream_id
"msg_011CdNqiFpivxnz6eDHQx4VM"
total_cost
0.00975
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
76.39%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
20
1
20
2
19
3
21
4
20
5
19
6
20
7
19
8
19
9
19