NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0N9SA721AW45SD47JP4E66
Run Details
Model:
GPT-5.5 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
14.3s
Cost:
$0.028555
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 needled the windows of Blackthorn Manor while Inspector Vale studied the corpse beside the grandfather clock at midnight alone. Lady Aurelia stood rigid in silk, her pearl necklace broken, scattering moons across the blood-dark parquet beneath her trembling feet. The butler claimed he heard nothing, though thunder had paused precisely when the library door slammed shut behind someone unseen. On the mantel, a chessboard waited midgame, its white king tipped over like a fainting witness in accusing silence tonight. Vale noticed muddy footprints crossing the Turkish rug, then vanishing before the locked conservatory doors as if swallowed completely there. A coal fire hissed softly, releasing a smell of roses, brandy, and something bitter underneath that made witnesses pale simultaneously. When the village constable lifted the victim's hand, a silver cufflink rolled into the light, engraved with Aurelia's crest clearly. Before anyone spoke, the clock struck one, and every face in the room confessed fear, except the dead man's own.
created_at
"2026-04-24T21:10:59.668Z"
4/24/2026, 9:10:59 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
13558
moderation_latency
(null)
generation_time
13975
tokens_prompt
46
tokens_completion
518
native_tokens_prompt
41
native_tokens_completion
945
native_tokens_completion_images
0
native_tokens_reasoning
740
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
0.028555
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_041cca3b7b3bb9290169ebdc63cc2481948b52af032f93803a"
is_byok
false
latency
312
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-1777065059-OvPnEgiUeeBjM225ghEN"
session_id
(null)
api_type
"completions"
id
"gen-1777065059-xZJpDPNKKWqnwP3cj4uS"
upstream_id
"resp_041cca3b7b3bb9290169ebdc63cc2481948b52af032f93803a"
total_cost
0.028555
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