NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKA0BDPM4P9SSF72AME77Q7
Run Details
Model:
GPT-5 Mini
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
38.2s
Cost:
$0.006624
Provider:
OpenAI
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
Fog pressed against the manor windows as midnight bell chimed, and someone realized the study contained a body last night. Detective Marlowe arrived with tired eyes, coat soaked, carrying a notebook that smelled faintly of tobacco and rain and grief. Candles guttered in silver sconces while servants hovered in doorways, whispering alibis and offering trembling, useful denials they insisted loudly. Blood had dried in a pale crescent on oriental rug, a crabbed signature left by violence and haste and secrecy. A half-finished glass of claret rocked gently on the mantel, beside a smashed photograph and a smoking cigar, unnoticed still. Neighbors had already gathered outside iron gates, faces blurred with curiosity, dread, and the warm gossip of town after supper. Marlowe's hands trembled only once, when he lifted the victim's wrist and found the faint, impossibly small bruise, an accusation. He looked up at those gathered, measuring their faces for lies, noting too how the house seemed older and colder.
created_at
"2026-02-16T13:25:38.139111+00:00"
2/16/2026, 1:25:38 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2572
moderation_latency
(null)
generation_time
38095
tokens_prompt
46
tokens_completion
995
native_tokens_prompt
41
native_tokens_completion
3307
native_tokens_completion_images
0
native_tokens_reasoning
3072
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
0.00662425
router
(null)
provider_responses
0
id
"resp_010c9912d50006c30169931aab8bf081969e55d04a8e25988f"
status
200
is_byok
false
latency
125
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771248299-lLuMGFUK885syZq7XrwN"
upstream_id
"resp_010c9912d50006c30169931aab8bf081969e55d04a8e25988f"
total_cost
0.00662425
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
95.0816%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
20
1
20
2
20
3
20
4
21
5
20
6
20
7
20