NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-09-01M4FZGW1YKQJ3G083SHGRMPQ6
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
3.0s
Cost:
$0.000171
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
63.74%
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 Harold Vance stepped through the grand oaken doorway. Candlelight flickered against portraits of stern, forgotten ancestors. Lady Millicent lay motionless upon the Persian rug. A silver letter opener protruded from her left shoulder. Nobody in the household had heard a single scream. Vance knelt beside the body and studied the dark stain. Her hands were clasped tightly around a crumpled note. The butler, Thomas Greer, hovered nervously near the staircase. "She asked me to bring tea at nine," he whispered. "Instead, I found her exactly like this, sir." Vance noticed the clock above the mantel had stopped. It read twenty minutes past eleven precisely. Somewhere beyond the windows, a car engine roared away. The detective pocketed the note before anyone could object. Its ink was smeared, but one word remained legible: "Tonight."
created_at
"2026-10-09T09:22:17.797Z"
10/9/2026, 9:22:17 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
783
moderation_latency
(null)
generation_time
2994
tokens_prompt
46
tokens_completion
227
native_tokens_prompt
62
native_tokens_completion
330
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
0.0001712
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791537737-mNA4ZiJmlY62Q2f7kEqh"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791537737-CpacnMkAaMUb7PrlV0D7"
upstream_id
"msg_011CfrRERx9VxewBz2jks3zC"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfrRERx9VxewBz2jks3zC"
is_byok
false
latency
780
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0001712
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
63.74%
Matches word count
n/a
neededClean
false
sentences
16
wordCounts
0
8
1
9
2
8
3
8
4
9
5
9
6
10
7
9
8
9
9
10
10
8
11
9
12
7
13
9
14
9
15
10