NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-09-01M4FXHCYRGAFJ0HMQ5XMTRTQH
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
3.3s
Cost:
$0.000191
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
67.40%
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 not stopped for three days straight now. Detective Mara Voss stepped carefully across the wet cobblestones. Yellow tape fluttered weakly against the iron gates of Hawthorne Manor. Officer Dan Ruiz met her at the entrance with a grim expression. "The body was found in the library," he said quietly. Mara pulled on her gloves and followed him inside. The air smelled of old paper, smoke, and something metallic. Portraits of stern ancestors watched them from dim, silent walls. A single lamp burned near the far window, casting long shadows. Beneath it lay Edwin Hawthorne, face down, still wearing his reading glasses. Mara knelt beside him and noticed a brass key clutched in his fist. Her eyes drifted to the overturned chair nearby. Someone had been in this room in a hurry. She glanced at the locked cabinet, its door hanging slightly open. Whoever killed Edwin Hawthorne had wanted something inside that cabinet. Mara stood up slowly and turned toward the hallway. Somewhere in the house, a door creaked shut.
created_at
"2026-10-09T08:47:38.092Z"
10/9/2026, 8:47:38 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
803
moderation_latency
(null)
generation_time
3089
tokens_prompt
46
tokens_completion
257
native_tokens_prompt
62
native_tokens_completion
370
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
0.0001912
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791535658-31gciVHUvXx624c3s3Or"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791535658-9PL9gWnzvrVfWPrXGVp9"
upstream_id
"msg_011CfrNb8g4rZNcmAAhzdUVf"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfrNb8g4rZNcmAAhzdUVf"
is_byok
false
latency
803
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0001912
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
67.40%
Matches word count
n/a
neededClean
false
sentences
17
wordCounts
0
10
1
9
2
11
3
12
4
10
5
9
6
10
7
10
8
11
9
12
10
13
11
8
12
9
13
11
14
10
15
9
16
8