NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHK9VHNKQAP20WVR2H5QB86X
Run Details
Model:
GPT-5
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
50.7s
Cost:
$0.032341
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
Rain hammered the cliffside village as the lighthouse beam jittered, slicing darkness while sirens approached the harbor road at midnight. Mara Ellison found the body behind the cannery, sprawled among nets, one shoe missing, eyes glassy beneath the flickering lamp. A playing card rested on his tongue, the queen of spades, blackened edges damp, daring anyone to understand the message. Detective Rowan Hale ducked under the tape, boots squeaking, eyes scanning fishermen huddled nearby, whispers looping like gulls overhead restlessly. "Lock the pier," he said, kneeling beside Mara, "and keep them talking; murder hates silence more than witnesses at night." Tidewater pawed at footprints leading nowhere, while the cannery clock chimed twelve twice, as if correcting time for a lie. Someone whispered the name Conrad Pike, salt baron, benefactor, bastard; the words snagged like hooks inside the fog and throats. Rowan smelled anise, unusual among tar and brine, recalling prison dice games, queen high determining debts paid in blood long-owed. Mara steadied herself, then pointed to his thumbnails, scraped raw, crescents packed with blue paint flecked like tidepool porcelain chips. The lighthouse blinked twice, surrendering darkness, and everyone looked smaller, as if the killer had already chosen another witness tonight.
created_at
"2026-02-16T13:23:13.137932+00:00"
2/16/2026, 1:23:13 PM
model
"openai/gpt-5-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6224
moderation_latency
(null)
generation_time
50500
tokens_prompt
46
tokens_completion
1100
native_tokens_prompt
41
native_tokens_completion
3229
native_tokens_completion_images
0
native_tokens_reasoning
2880
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
0.03234125
router
(null)
provider_responses
0
id
"resp_0092da01df0065100169931a0e13cc8190b3c3335fb93227e2"
status
200
is_byok
false
latency
154
endpoint_id
"7c2f859a-7890-4e8e-b1de-1cd1c0a800b4"
provider_name
"OpenAI"
model_permaslug
"openai/gpt-5-2025-08-07"
api_type
"completions"
id
"gen-1771248142-Cy6M167ozn6yzzJRcX3r"
upstream_id
"resp_0092da01df0065100169931a0e13cc8190b3c3335fb93227e2"
total_cost
0.03234125
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
96.0653%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
21
8
20
9
20