NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAF8G89HVFBT5CWRVYCYDJ
Run Details
Model:
GPT-5.2
Test:
N-Length Sentences
Scenario:
Write sentences with 5 words each
Duration:
14.1s
Cost:
$0.010040
Provider:
OpenAI
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 5 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
Fog clung to Marrow Street. Detective Lysa arrived before dawn. A bell tolled, then stopped. Neighbors watched behind curtained windows. The townhouse door stood ajar. Inside, candles burned without flicker. A man lay beneath roses. His throat wore a ribbon. No blood stained the carpet. Only rainwater pooled near stairs. Lysa noted footprints, oddly absent. Someone had scrubbed the hallway. On the mantle, a clock. Its hands pointed at thirteen. A note rested under glass. It read: 'Tell nobody, Lysa'. She hadn't signed the register. Yet her name waited, inked.
created_at
"2026-02-16T13:33:22.851384+00:00"
2/16/2026, 1:33:22 PM
model
"openai/gpt-5.2-20251211"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
5572
moderation_latency
(null)
generation_time
13917
tokens_prompt
46
tokens_completion
484
native_tokens_prompt
41
native_tokens_completion
712
native_tokens_completion_images
0
native_tokens_reasoning
560
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
0.01003975
router
(null)
provider_responses
0
id
"resp_0a1ba905b94634860169931c940f4c8194bd5533155812770e"
status
200
is_byok
false
latency
159
endpoint_id
"f00142c2-6a93-49ce-9e36-5593b904ce3b"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.2-20251211"
api_type
"completions"
id
"gen-1771248787-a7SwcSF7QXFm9lgMSkiT"
upstream_id
"resp_0a1ba905b94634860169931c940f4c8194bd5533155812770e"
total_cost
0.01003975
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
18
wordCounts
0
5
1
5
2
5
3
5
4
5
5
5
6
5
7
5
8
5
9
5
10
5
11
5
12
5
13
5
14
5
15
5
16
5
17
5