NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0NHVJQKRQZ6C4A873GH7QG
Run Details
Model:
GPT-5.5
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
5.0s
Cost:
$0.004435
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
42.88%
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 silver lines across Blackthorn Manor while Inspector Vale counted thirteen dinner plates, though only twelve guests waited. The grandfather clock stopped at midnight, and beneath its hands, Lord Ashbury lay smiling with an ivory dagger protruding. No one screamed until the candles blew out, leaving perfume, wet wool, and one whisper: “He deserved worse tonight.” When light returned, every face displayed horror, yet each right hand remained hidden beneath the tablecloth deliberately. Vale noticed bloodless cuffs, muddy hems, and a single black chess queen resting inside the dead man's open palm. Outside, the storm erased carriage tracks, while inside, the murderer learned the inspector had locked every door himself.
created_at
"2026-04-24T21:15:24.128Z"
4/24/2026, 9:15:24 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
648
moderation_latency
(null)
generation_time
4763
tokens_prompt
46
tokens_completion
195
native_tokens_prompt
41
native_tokens_completion
141
native_tokens_completion_images
0
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
"completed"
usage
0.004435
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_015a6d0e8294e5bc0169ebdd6c348881968992aba09b5b6faf"
is_byok
false
latency
274
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-1777065324-kaCqIbzphoaeQ5GxBqFP"
session_id
(null)
api_type
"completions"
id
"gen-1777065324-lf5Yy1hg6aZkNe1u1pVG"
upstream_id
"resp_015a6d0e8294e5bc0169ebdd6c348881968992aba09b5b6faf"
total_cost
0.004435
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
42.88%
Matches word count
n/a
neededClean
false
sentences
6
wordCounts
0
19
1
19
2
19
3
17
4
19
5
18