NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKB5815NAZJXNJH9EYGQ5DT
Run Details
Model:
GPT-5 Mini
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
39.6s
Cost:
$0.003246
Provider:
OpenAI
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 hammered the cobblestones as Detective Marlowe arrived at midnight. A crowd clustered behind yellow tape, breathing nervous, damp air. On the riverbank, a body lay pale beneath the gaslight. Her dress was torn, pearl necklace buried in cold mud. No footprints led directly away, only a smudge of crimson. Detective Marlowe crouched, eyes narrow, calculating the impossible sequence backwards. The coroner lit a cigarette, studying the small, precise wound. Someone whispered the name 'Evelyn' and the crowd inhaled sharply. Marlowe remembered a photograph: Evelyn smiling at a summer party. There would be lies, alibis, and secrets buried under wallpaper.
created_at
"2026-02-16T13:45:48.886133+00:00"
2/16/2026, 1:45:48 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3691
moderation_latency
(null)
generation_time
39553
tokens_prompt
46
tokens_completion
784
native_tokens_prompt
41
native_tokens_completion
1618
native_tokens_completion_images
0
native_tokens_reasoning
1408
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
0.00324625
router
(null)
provider_responses
0
id
"resp_04609c13a438d28f0169931f64790081979a86232d3a0b540e"
status
200
is_byok
false
latency
138
endpoint_id
"c4f66d01-20b0-4c27-a225-438ea22fda43"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-mini-2025-08-07"
api_type
"completions"
id
"gen-1771249508-SzJDOWyOnjeMvuTxsuI6"
upstream_id
"resp_04609c13a438d28f0169931f64790081979a86232d3a0b540e"
total_cost
0.00324625
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.0000%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
10
1
10
2
10
3
10
4
10
5
10
6
10
7
10
8
10
9
10