NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0NZND0HGV7NM95TXNCFWZX
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
17.0s
Cost:
$0.037345
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
At midnight, the grandfather clock stopped, and every candle in Blackthorn Manor guttered as if remembering a secret long buried. Inspector Vale arrived through rain, his coat shining black, while servants huddled beneath portraits of unsmiling ancestors in cold silence. Lady Maribel lay beside the music room piano, one gloved hand clenched around a torn crimson ribbon and silver key. No one admitted hearing screams, though the storm had paused for three impossible minutes before the discovery in the dark. Her husband stood rigidly by the hearth, smelling faintly of brandy, tobacco, and freshly turned garden earth after midnight rain. In the corridor, a maid wept over broken lilies, insisting they had not been there at supper or afterward either. Vale noticed muddy footprints crossing the polished floor, stopping neatly beneath the locked conservatory door from inside the house itself. Then the dead woman's canary began singing upstairs, inside a room everyone swore was empty until dawn's first bell rang.
created_at
"2026-04-24T21:22:56.564Z"
4/24/2026, 9:22:56 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
15816
moderation_latency
(null)
generation_time
16816
tokens_prompt
46
tokens_completion
528
native_tokens_prompt
41
native_tokens_completion
1238
native_tokens_completion_images
0
native_tokens_reasoning
1034
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
0.037345
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0464b76902979a3f0169ebdf30a85c8196bb03e55cd509ea2d"
is_byok
false
latency
345
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-1777065776-3vdWOSerkttT5nDjmdRD"
session_id
(null)
api_type
"completions"
id
"gen-1777065776-ZKput7SpJ7nIKxBKuvyD"
upstream_id
"resp_0464b76902979a3f0169ebdf30a85c8196bb03e55cd509ea2d"
total_cost
0.037345
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