NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07N331MWVRSSYP9SEAQ86T
Run Details
Model:
GPT-5.4 Mini
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
1.3s
Cost:
$0.000625
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
91.36%
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 drummed softly against the mansion, muting distant, uneasy whispers. Inspector Vale arrived late, carrying suspicion like a second coat. Inside, candles flickered, exposing marble faces and trembling, polished silver. The host smiled too widely, though grief already hollowed his cheeks. Someone had screamed earlier, and nobody could agree where. A portrait had fallen, revealing a fresh stain beneath it. Vale noticed three clocks, each stopped at different times. The guests avoided mirrors, as if reflections might accuse them. Then the lights died, and a body hit the floor.
created_at
"2026-03-18T10:25:24.593Z"
3/18/2026, 10:25:24 AM
model
"openai/gpt-5.4-mini-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
449
moderation_latency
(null)
generation_time
1183
tokens_prompt
46
tokens_completion
156
native_tokens_prompt
41
native_tokens_completion
132
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
0.00062475
router
(null)
provider_responses
0
endpoint_id
"9ee065b2-3d1c-43bc-bdd7-28af3b148282"
id
"resp_06bc48d9981c91950169ba7d94a5e08195bc7d8acd0b4105c8"
is_byok
false
latency
229
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-1773829524-VhWpcYOGpqpRXVj2gB6x"
upstream_id
"resp_06bc48d9981c91950169ba7d94a5e08195bc7d8acd0b4105c8"
total_cost
0.00062475
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
91.36%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
10
1
10
2
10
3
11
4
9
5
10
6
9
7
10
8
10