NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PXPAC5M772A3P104DRT36
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
17.8s
Cost:
$0.033535
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 20 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
Rain rattled the conservatory windows as Inspector Vale arrived at Blackthorn Hall, summoned by a bell no servant admitted ringing. Inside, twelve guests waited beneath portraits darkened by smoke, each pretending not to watch the library's bolted door too closely. Lady Blackthorn sat nearest the fire, her gloves spotless, her face ash pale, her teacup trembling against its saucer's rim. Vale removed his wet hat slowly, noticing mud on the Persian rug forming a trail toward the locked room ahead. Before he could speak, a muffled thud sounded within the library, followed by music from an unseen gramophone turning itself. The butler swore the key was missing, though Vale saw its outline pressing through the man's waistcoat pocket plainly enough. When the door finally opened, Lord Blackthorn lay across his desk, ink blackening the wound beneath his white silk collar. On the blotter, drying beside his hand, someone had written Vale's name in blood, using the victim's fountain pen carefully.
created_at
"2026-04-24T21:39:20.533Z"
4/24/2026, 9:39:20 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
16397
moderation_latency
(null)
generation_time
17562
tokens_prompt
46
tokens_completion
1020
native_tokens_prompt
41
native_tokens_completion
1111
native_tokens_completion_images
0
native_tokens_reasoning
900
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
"completed"
usage
0.033535
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_006f0b22a14bafa50169ebe308a4588194b6c5db032d6caaed"
is_byok
false
latency
335
model_permaslug
"openai/gpt-5.5-20260423"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777066760-vqFKbPJd9u5COvrbzJCm"
session_id
(null)
api_type
"completions"
id
"gen-1777066760-Wq3vBND1pqW2FiDiK4cP"
upstream_id
"resp_006f0b22a14bafa50169ebe308a4588194b6c5db032d6caaed"
total_cost
0.033535
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20