NC Bench
Overview
About
Tests
Models
Vendors
Run: 2026-02-16-01KHKA11MFR1QZFNQC561T9YMM
Run Details
Model:
GPT-5 Mini
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
26.7s
Cost:
$0.004388
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 stitched black seams across the town as Detective Marlowe stepped under the lamplight, observing the silent house beyond windows. A single porch light flickered then died, leaving only the crooked shadow where someone had once stood and rain whispered. Inside, the parlor smelled of lemon polish and spilled wine, the rug folded back like a mouth revealing secrets today. On the chaise, Ms. Ellery slumped with a letter opener buried between ribs, pale fingers relaxed as if forgiving still. No sign of forced entry, no footprints on wet porch boards; only an overturned chair and a scent of jasmine. Neighbors murmured behind curtains, confessing facts in whispers while Detective Marlowe catalogued contradictions like contraband in a ledger old notebook. He found a photograph face-down, two laughing figures, one circled in dry ink, a memory someone had wanted erased quietly. The clock on the mantel stopped at three-fourteen, its hands frozen like witnesses refusing to speak the night any truth.
created_at
"2026-02-16T13:25:49.317493+00:00"
2/16/2026, 1:25:49 PM
model
"openai/gpt-5-mini-2025-08-07"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3957
moderation_latency
(null)
generation_time
26051
tokens_prompt
46
tokens_completion
980
native_tokens_prompt
41
native_tokens_completion
2189
native_tokens_completion_images
0
native_tokens_reasoning
1920
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
0.00438825
router
(null)
provider_responses
0
id
"resp_05aae0de5da405b80169931ac24a048194b6c96251c5c79f62"
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-1771248322-NVpZ4QqRcnkwwoo57ZyU"
upstream_id
"resp_05aae0de5da405b80169931ac24a048194b6c96251c5c79f62"
total_cost
0.00438825
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
90.1633%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
21
7
21