NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-10-08-01M4D9Y9C573KN7CP1952BHPFE
Run Details
Model:
Claude Haiku 5.5 (Reasoning, Medium)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
3.6s
Cost:
$0.000213
Provider:
Claude Platform on AWS
Evaluation summary
Score
Evaluator
Details Link
74.87%
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 Sarah Hollis pulled her collar tight against the wind. Officers had cordoned off the old Brennan mansion overnight. Yellow tape snapped violently across the broken front gate. Nobody inside had answered the door since Tuesday. Her partner, Marcus Cole, met her beneath the dripping oak. "Body's in the study," he said, already walking ahead. She followed him up the cracked marble steps slowly. Inside, the air smelled of smoke and old lilies. A single lamp still burned on the mahogany desk. Beside it lay Victor Brennan, face down, motionless. An empty brandy glass rested near his outstretched hand. Sarah knelt carefully and studied the faint red stain. Something about the angle of the body felt wrong. Marcus crouched beside her, frowning at the shattered window. "Glass fell outward," he murmured, "so someone broke in." "Or someone wanted us to think exactly that," Sarah replied. She turned slowly, scanning the room for anything out of place. On the mantel, a clock had stopped at 11:42. Her heart quickened, because she had heard that exact time before.
created_at
"2026-10-08T08:26:39.887Z"
10/8/2026, 8:26:39 AM
model
"anthropic/claude-haiku-5.5-20261007"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
739
moderation_latency
(null)
generation_time
3543
tokens_prompt
46
tokens_completion
288
native_tokens_prompt
62
native_tokens_completion
413
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
0.0002127
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.21.0; linux; x64))"
http_referer
(null)
request_id
"req-1791447999-k3PtRplFrXNFqLQ11Amp"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1791447999-A2xLuRPD6sAIEUq0SAbQ"
upstream_id
"msg_011CfpTBTmBBp7x8d3hBwgX7"
provider_responses
0
endpoint_id
"b6cdf493-3a61-441f-a134-e7944fddb980"
id
"msg_011CfpTBTmBBp7x8d3hBwgX7"
is_byok
false
latency
739
model_permaslug
"anthropic/claude-haiku-5.5-20261007"
provider_name
"Claude Platform on AWS"
status
200
total_cost
0.0002127
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
74.87%
Matches word count
n/a
neededClean
false
sentences
20
wordCounts
0
10
1
10
2
9
3
9
4
8
5
10
6
9
7
9
8
9
9
9
10
8
11
9
12
9
13
9
14
9
15
9
16
10
17
11
18
9
19
11