NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKAXMHF3V8E0Z60Q7AX07V6
Run Details
Model:
GPT-5.1
Test:
N-Length Sentences
Scenario:
Write sentences with 5 words each
Duration:
20.4s
Cost:
$0.013951
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
Rain hammered the ancient manor. Lightning stitched across the clouds. Detective Mara Quinn arrived late. Patrol cars crowded the driveway. Glass glittered like frost underfoot. The front door yawned crooked. Inside, voices tangled with static. A radio crackled on standby. Uniforms parted as Mara entered. The living room smelled metallic. Blood varnished the Persian rug. A body lay beside fireplace. Eyes stared upward, glassy, surprised. Someone had arranged the hands. Fingers pointed toward the mantelpiece. There, a single photograph remained. Every other frame lay shattered. Mara studied the intact picture. Bride and groom smiled forever. Tonight, only one survived marriage. Behind Mara, someone quietly sobbed. She turned toward the sound. A man clutched a handkerchief. Blood spotted its monogrammed corner. He whispered, barely above thunder. I only locked the door. Someone was already screaming inside.
created_at
"2026-02-16T13:41:19.7646+00:00"
2/16/2026, 1:41:19 PM
model
"openai/gpt-5.1-20251113"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
15580
moderation_latency
(null)
generation_time
20154
tokens_prompt
46
tokens_completion
556
native_tokens_prompt
41
native_tokens_completion
1390
native_tokens_completion_images
0
native_tokens_reasoning
1169
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
0.01395125
router
(null)
provider_responses
0
id
"resp_04c99cb099c1e7830169931e6b206881948cc23e52e6a4ceaf"
status
200
is_byok
false
latency
147
endpoint_id
"764eb97f-8bab-4326-b29b-7a8799b00a70"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5.1-20251113"
api_type
"completions"
id
"gen-1771249259-pbYk1Nh1kQbhtEATCn7Q"
upstream_id
"resp_04c99cb099c1e7830169931e6b206881948cc23e52e6a4ceaf"
total_cost
0.01395125
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
27
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
18
5
19
5
20
5
21
5
22
5
23
5
24
5
25
5
26
5