NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PBX4RPPHFX0ZCDPB6M74R
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
22.7s
Cost:
$0.050245
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 stitched threads across Blackwood Manor's windows as Inspector Vale arrived, summoned by a bell no living hand rang twice. Inside, twelve guests waited beneath chandeliers, their faces pale with secrets, while Lord Ashbury lay cooling in the library alone. A chessboard rested beside his chair, all pieces standing except the black king, which was missing from the board entirely. On the carpet, a single white rose bled crimson where someone had pressed it into the dead man's wound deeply. Vale removed his gloves slowly, noticing the fireplace smoke drift sideways, though every door and window stood firmly shut tight. Lady Ashbury whispered that her husband had feared supper, clocks, and the portrait watching from above the mantel each night. Before Vale could answer, the hall clock struck thirteen, and someone laughed behind the locked library door upstairs in darkness. The inspector studied the guests and knew one of them had already arranged another death before midnight with terrible care.
created_at
"2026-04-24T21:29:37.696Z"
4/24/2026, 9:29:37 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
22118
moderation_latency
(null)
generation_time
22372
tokens_prompt
46
tokens_completion
820
native_tokens_prompt
41
native_tokens_completion
1668
native_tokens_completion_images
0
native_tokens_reasoning
1474
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
0.050245
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_08cf1b9cbc5b8d230169ebe0c1c8108195b1ae869667e39cf7"
is_byok
false
latency
254
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-1777066177-D3lRPfp3FXVVflJOK7FI"
session_id
(null)
api_type
"completions"
id
"gen-1777066177-0uaRSQcThfxRz0w3Znhy"
upstream_id
"resp_08cf1b9cbc5b8d230169ebe0c1c8108195b1ae869667e39cf7"
total_cost
0.050245
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