NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAXEFQP1S6HMWG7XA9CFF4
Run Details
Model:
GPT-5
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
28.3s
Cost:
$0.017391
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 braided the streetlights as midnight bled into restless cobblestones. Detective Mara Quinn arrived, umbrella useless against the sideways storm. Sirens dwindled behind her, leaving footsteps like questions on stone. The mansion crouched ahead, windows blinking, a sullen animal watching. Inside, a chandelier trembled, whispering crystal prayers to nobody tonight. Butler Cormac waited stiffly, lapel blooming a brownish rainflower stain. He bowed, voice raw: the countess fell, and wouldn't wake. Mara followed echoes to the parlor, air sugared with lilacs. There, the countess reclined crookedly, champagne flutes surrounding like sentries. Her pearl necklace snapped, beads spelling panic across the carpet. A window gaped open; curtains clawed, desperate hands without bodies. Thunder applauded murder while a grandfather clock counted the alibi. Mara knelt, tasting copper air, inspecting lipstick on shattered flute. It smeared clockwise, not from sipping, but careful, guiding pressure. Cormac hovered, as lightning mapped his face with confession lines. She asked for matches; he produced three, but carried four. The fourth lay missing, exactly like the countess's purple pulse. Rain hissed harder, as candles shortened, like secrets losing patience. Somewhere upstairs, water ran, though nobody admitted bathing recently tonight. Mara pocketed a bead, and the room exhaled, listening closely.
created_at
"2026-02-16T13:41:21.426278+00:00"
2/16/2026, 1:41:21 PM
model
"openai/gpt-5-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4493
moderation_latency
(null)
generation_time
27945
tokens_prompt
46
tokens_completion
1198
native_tokens_prompt
41
native_tokens_completion
1734
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
0.01739125
router
(null)
provider_responses
0
id
"resp_05f85425fdb4acc80169931e64f5948193800dec733b7b82ca"
status
200
is_byok
false
latency
160
endpoint_id
"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-2025-08-07"
api_type
"completions"
id
"gen-1771249252-61HIu6Vyd68BOivdRjTo"
upstream_id
"resp_05f85425fdb4acc80169931e64f5948193800dec733b7b82ca"
total_cost
0.01739125
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
20
wordCounts
0
10
1
10
2
10
3
10
4
10
5
10
6
10
7
10
8
10
9
10
10
10
11
10
12
10
13
10
14
10
15
10
16
10
17
10
18
10
19
10