NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-09-01M4G0KBC06F80DES9CC7AH1DB
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
3.2s
Cost:
$0.000216
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
60.38%
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 Miles Corrigan stepped out of his battered sedan. Thunder rolled across the moors like distant cannon fire. Inside the foyer, a single lamp flickered weakly above the staircase. Lady Evelyn Thorne lay motionless at the bottom of the steps. Her silver necklace glinted against the dark marble floor. Corrigan knelt beside her and checked for a pulse. His fingers found nothing but cold, unmoving skin. Behind him, the butler cleared his throat nervously. "Nobody has touched anything, Detective," he whispered softly. Corrigan noticed a teacup shattered near the doorway. Its amber liquid had spread into a dark, sticky stain. Upstairs, a door creaked open slowly and deliberately. Someone was watching them from the shadows above. Corrigan rose slowly and pulled out his notebook. "Everyone stays in the drawing room until morning," he announced. The butler nodded, but his hands were trembling badly. Corrigan made a mental note of that small detail. Outside, the storm grew louder against the tall windows. And somewhere in the house, a clock began to chime.
created_at
"2026-10-09T09:41:07.592Z"
10/9/2026, 9:41:07 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
746
moderation_latency
(null)
generation_time
3204
tokens_prompt
46
tokens_completion
284
native_tokens_prompt
62
native_tokens_completion
420
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
0.0002162
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791538867-FuMBZqMpilj8fN2q3u4D"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791538867-027DiB5s5z4WfhgTRVti"
upstream_id
"msg_011CfrSfhxNqMcZj1SfxdC9H"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfrSfhxNqMcZj1SfxdC9H"
is_byok
false
latency
746
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0002162
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
60.38%
Matches word count
n/a
neededClean
false
sentences
20
wordCounts
0
8
1
9
2
9
3
11
4
11
5
9
6
9
7
8
8
8
9
8
10
8
11
10
12
8
13
8
14
8
15
10
16
9
17
9
18
9
19
10