NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DAKR006B429YPM5SBVCNVK
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Medium)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
3.3s
Cost:
$0.000180
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
73.95%
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 fell hard on Ashford Manor tonight. Detective Mara Quinn arrived at the gates after midnight. Her flashlight cut through the thick, dripping fog ahead. Somewhere inside, a clock struck twelve, slow and mournful. The butler met her at the door, pale and trembling. "Lord Harrow is dead," he whispered, glancing nervously behind him. Mara stepped across the threshold, boots squelching on marble tiles. The study door stood slightly ajar, spilling dim amber light. Inside, the old man sat slumped over his mahogany desk. A single silver letter opener protruded from his back. Mara knelt beside the body, studying each detail carefully. The ink on his blotter was still wet. Someone had been writing him a letter moments ago. Her eyes drifted toward the open window, where a curtain fluttered. Outside, footsteps crunched quickly across the gravel and vanished. Mara rose slowly, her pulse quickening with dread. Tonight, somebody in this house had lied to her.
created_at
"2026-10-08T08:38:22.984Z"
10/8/2026, 8:38:22 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
684
moderation_latency
(null)
generation_time
3232
tokens_prompt
46
tokens_completion
242
native_tokens_prompt
62
native_tokens_completion
347
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
0.0001797
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791448702-YHWEVPme8MjKbl5Am44u"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791448702-d44mAJwtfp4ZGp8nDblG"
upstream_id
"msg_011CfpU5J3yuc9ZhJrNjLoR6"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpU5J3yuc9ZhJrNjLoR6"
is_byok
false
latency
684
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0001797
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
73.95%
Matches word count
n/a
neededClean
false
sentences
17
wordCounts
0
8
1
9
2
9
3
9
4
10
5
10
6
10
7
10
8
10
9
9
10
9
11
8
12
9
13
11
14
9
15
8
16
9