NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KK9PSKQ46FT84QF86XV5GPKD
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
27.0s
Cost:
$0.027162
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
94.38%
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 manor windows as Inspector Vale arrived, summoned before dawn by a trembling footman who refused entering alone. In the library, the clock had stopped at three, and Lady Harrow lay beside the hearth, smiling unnaturally in death. A chessboard waited on the table, black queen toppled, while six untouched glasses caught lightning like accusing eyes that night. No door stood open, no window unlatched, yet mud glistened across the Persian rug in deliberate, inward footsteps from outside. Vale removed his gloves, noticing the victim's wedding ring missing, though a pale band remained upon her finger still visible. Then the butler whispered that everyone in the house had heard the scream, and nobody admitted hearing it twice tonight. Vale looked again at Lady Harrow's smile and understood, with sudden dread, that someone had posed her after death.
created_at
"2026-03-09T16:27:29.591Z"
3/9/2026, 4:27:29 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
25316
moderation_latency
(null)
generation_time
26605
tokens_prompt
46
tokens_completion
512
native_tokens_prompt
41
native_tokens_completion
1804
native_tokens_completion_images
0
native_tokens_reasoning
1617
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.0271625
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_03bd239c1dcbd45d0169aef4f1c0e8819692971854dbf145ff"
is_byok
false
latency
193
model_permaslug
"openai/gpt-5.4-20260305"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773073649-LQqOiWW65Y0C3rTJEL5M"
upstream_id
"resp_03bd239c1dcbd45d0169aef4f1c0e8819692971854dbf145ff"
total_cost
0.0271625
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
94.38%
Matches word count
n/a
neededClean
false
sentences
7
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
19