NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-09-01M4FY0WWPSMA93X5F4AK24K77
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
8.4s
Cost:
$0.000880
Provider:
Claude Platform on AWS
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 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 falling over Harrowgate for three days when Detective Mara Quill arrived at the manor's iron gates. Inside, the house smelled of wet wool, burnt sugar, and something sharper that she could not yet name, even now. Constable Thomas Greaves met her in the hallway, his face unusually pale and his notebook trembling in his shaking hand. Lord Edmund Ashby had been found at the foot of the grand staircase, a letter opener buried in his chest. Mara knelt beside the body, noting the dried mud on his boots and the candle guttering on the landing above. Nobody had touched the candle, which meant someone had lit it after the killing and then left in a hurry. Mara looked up at the gallery, where eleven guests had gathered, each one watching her with careful, unreadable, hungry eyes.
created_at
"2026-10-09T08:56:05.788Z"
10/9/2026, 8:56:05 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2304
moderation_latency
(null)
generation_time
8335
tokens_prompt
46
tokens_completion
433
native_tokens_prompt
62
native_tokens_completion
1748
native_tokens_completion_images
(null)
native_tokens_reasoning
1476
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
0.0008802
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791536165-s7Crm0zpXjjxb8AeBF5U"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791536165-2VbRizL0kYEOL2eODKle"
upstream_id
"msg_011CfrPEYgURTxxN91KPgiU9"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfrPEYgURTxxN91KPgiU9"
is_byok
false
latency
747
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0008802
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
100.00%
Matches word count
n/a
neededClean
false
sentences
7
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20