NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0ABTWK82RGQWJJW0WKGARR
Run Details
Model:
GPT-5.4 Mini
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
1.5s
Cost:
$0.000593
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
85.60%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 10 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
Rain stitched the harbor into silver shrouds before dawn arrived. Detective Mara Vale climbed the steps toward Blackthorn Manor. The butler waited, pale and trembling, beneath the candlelit archway. Inside, the library smelled of smoke, roses, and secrets. Lord Blackthorn lay beside the hearth, one hand clutching letters. His eyes stared upward, accusing someone already gone elsewhere. Mara noticed muddy footprints crossing the Persian rug silently. A shattered window whispered of intrusion, but not escape. Then she saw the clock: it had stopped at midnight.
created_at
"2026-03-18T11:12:47.009Z"
3/18/2026, 11:12:47 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
818
moderation_latency
(null)
generation_time
1414
tokens_prompt
46
tokens_completion
151
native_tokens_prompt
41
native_tokens_completion
125
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)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.00059325
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_0235441f037024710169ba88af12148190a317d69ec453dd10"
is_byok
false
latency
168
model_permaslug
"openai/gpt-5.4-mini-20260317"
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-1773832367-B51k20meK0r1QKnSXqAz"
upstream_id
"resp_0235441f037024710169ba88af12148190a317d69ec453dd10"
total_cost
0.00059325
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
85.60%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
10
1
9
2
10
3
9
4
10
5
9
6
9
7
9
8
10