NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4DYKEV53E53EHSFRN0R0ZXX
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Max)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
3m 7s
Cost:
$0.024839
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
95.45%
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 falling since early Tuesday evening. Detective Mercer stood beneath the flickering lamp outside Ashgrove Manor. She pulled her collar higher and counted the dark windows. Somewhere inside, a dog barked twice and then fell silent. Constable Reid met her at the door, his face pale. Portraits of stern ancestors watched them from the corridor walls. A woman in grey silk waited motionless on the stairs. Reid swallowed hard, then whispered, "Nobody has moved him yet." The library smelled of cold cigars and something sharper beneath. Edmund Vane lay slumped across his desk, one hand outstretched. A fire had burned down to embers in the grate. Only one teacup rested on the tray beside the decanter. A second saucer sat empty beside it, its cup missing. Mercer crouched beside the body and noticed the stained fingertips. Dark ink had bled into the creases of his skin. An uncapped pen lay beside an unfinished letter to Ruth. It began, "My dearest Ruth, I know what you did." Mercer asked Reid, "Who else has been in this room?" Reid stared at the carpet and did not answer her. Beyond the door, a floorboard creaked and a shadow shifted. The mantel clock had halted at a quarter past eleven. Someone had stopped its pendulum by hand, Mercer realised quietly. That missing cup, she suspected, had been washed and hidden. Whoever killed Edmund Vane had wanted the hour to lie.
created_at
"2026-10-08T14:27:45.136Z"
10/8/2026, 2:27:45 PM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3227
moderation_latency
(null)
generation_time
186562
tokens_prompt
46
tokens_completion
6900
native_tokens_prompt
62
native_tokens_completion
49665
native_tokens_completion_images
(null)
native_tokens_reasoning
49151
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
0.0248387
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791469665-QwCLVpHFwnFtE9xxM1qf"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791469665-zrDLp8uVRGIfsYgMuyKd"
upstream_id
"msg_011CfpviWWdonaiQmH4xwr7o"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpviWWdonaiQmH4xwr7o"
is_byok
false
latency
997
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0248387
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
95.45%
Matches word count
n/a
neededClean
false
sentences
22
wordCounts
0
10
1
10
2
10
3
10
4
10
5
10
6
10
7
10
8
10
9
10
10
10
11
10
12
10
13
10
14
10
15
10
16
30
17
10
18
10
19
10
20
10
21
10