NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DZVTNNG1HBJJS102CBER6R
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Max)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
2m 28s
Cost:
$0.020778
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
90.00%
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 rain had been drumming on Blackwood Manor since midnight. Inspector Mara Quill arrived at dawn, soaked to the skin. Edmund Garrow lay face down before the cold library fireplace. Blood had pooled beneath his head, dark and already drying. Shards of crystal glittered across the Persian rug near him. Two brandy glasses stood on the mantel, one half full. The grandfather clock had stopped at a quarter past midnight. Beyond the desk, French doors hung open onto the garden. Muddy footprints led from those doors straight to the hearth. Sergeant Tom Reddick whispered, "Nobody has touched a single thing." Mara knelt beside the body and studied the victim's hands. Ink stained his right fingers, though he never wrote letters. In the grate, one scrap of paper survived the flames. Mara lifted it free, and one legible word read Julian. Behind her, a loose floorboard creaked beneath a hurried step. Vivienne Garrow stood frozen in the doorway, wrapped in silk. Her gaze found the body, then lingered on the scrap. "Forgive me, madam, but where exactly were you last night?" Her lips barely moved as she answered, calm and precise. "Asleep upstairs, Inspector, in a separate bedroom for three years." Mara noticed fresh mud darkening the hem of Vivienne's gown. Somewhere above them, a door had clicked shut very softly.
created_at
"2026-10-08T14:49:47.969Z"
10/8/2026, 2:49:47 PM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2544
moderation_latency
(null)
generation_time
148431
tokens_prompt
46
tokens_completion
5132
native_tokens_prompt
62
native_tokens_completion
41543
native_tokens_completion_images
(null)
native_tokens_reasoning
41054
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
0.0207777
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791470987-uoy42aeHrR5E6rvhtZbv"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791470987-69FEoqjrLtNboWEoWPNG"
upstream_id
"msg_011CfpxQ237CA8dLbVqq3SPC"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpxQ237CA8dLbVqq3SPC"
is_byok
false
latency
858
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0207777
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Claude Platform on AWS"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
90.00%
Matches word count
n/a
neededClean
false
sentences
20
wordCounts
0
10
1
10
2
10
3
10
4
10
5
10
6
10
7
10
8
10
9
20
10
10
11
10
12
10
13
10
14
10
15
10
16
20
17
10
18
10
19
10