NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4E0C8M5QA7483HGQJWV6S1F
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Max)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
1m 58s
Cost:
$0.016522
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
90.91%
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 had been drumming against the windows of Blackwood Manor since dusk, and nobody inside had slept a wink. Inspector Margaret Hale arrived at half past one, her coat soaked and her patience worn thin by the long drive. Lord Edmund Ashworth sat slumped in his leather chair, a single crimson stain spreading steadily across his white linen shirt. The study door had been locked from inside, and the only key still hung on a chain around his neck. Constable Ross stood beside the cold fireplace, turning his hat nervously in his hands and carefully avoiding her unwavering gaze. Hale turned sharply toward Ross and said, "Nobody leaves until I have personally spoken with every soul under this roof." Across the hall, the Ashworth family had gathered in the library, whispering like nervous conspirators beneath a single dim lamp. On the desk beside the body rested a silver carriage clock, its hands stopped at precisely a quarter to midnight. Hale stepped carefully around the blood, noting the empty brandy glass, the smudged ink, and muddy footprints by the window. Tucked beneath the blotter lay an unfinished letter addressed to Inspector Hale herself, dated only three days before the murder. The first line read simply: "Margaret, if you are reading this, one of them has finally succeeded in killing me." Somewhere above, a door slammed shut, and Hale realized with a chill that the killer was still in the house.
created_at
"2026-10-08T14:58:46.549Z"
10/8/2026, 2:58:46 PM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2420
moderation_latency
(null)
generation_time
118147
tokens_prompt
46
tokens_completion
4298
native_tokens_prompt
62
native_tokens_completion
33032
native_tokens_completion_images
(null)
native_tokens_reasoning
32549
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
0.0165222
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791471526-G2UqAvMPEKX8NzIEJufr"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791471526-gpCBlMqQ238gYZWh8Stv"
upstream_id
"msg_011Cfpy5iXWmz3gt6SrdEvg4"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011Cfpy5iXWmz3gt6SrdEvg4"
is_byok
false
latency
790
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0165222
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
90.91%
Matches word count
n/a
neededClean
false
sentences
11
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20
8
20
9
20
10
40