NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM07HW0CD29QAQCF0RA0PBEZ
Run Details
Model:
GPT-5.4 Nano (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
5.3s
Cost:
$0.001209
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
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
The rain hammered Marrowick Station when Detective Hale arrived, suitcase clutched tight, hearing whispers from Porter's platform below at midnight. A conductor's whistle had stopped abruptly, and silence sat like frost across the empty ticket office windows all around tonight. Behind the luggage shed, someone found the mayor sprawled, throat cut neatly, lantern light pooling around his shoes alone there. Hale knelt without gloves, sniffing iron and cedar, then noticed a cufflink stamped with a raven crest engraved in silver. Three suspects hovered nearby: Porter's brother, the skeptical nurse, and Councilman Voss with muddy boots fresh from tracks outside town. Each insisted innocence, yet their stories tangled around a missing key said to open the freight vault by dawn yesterday. Hale requested names again, watching how the nurse avoided rainwater stains on the railings near the stairs most carefully then. When lightning flared, the ravens on the cufflink seemed to twitch, as if still listening for the next footstep coming.
created_at
"2026-03-18T10:23:39.035Z"
3/18/2026, 10:23:39 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
4664
moderation_latency
(null)
generation_time
5154
tokens_prompt
46
tokens_completion
269
native_tokens_prompt
41
native_tokens_completion
961
native_tokens_completion_images
0
native_tokens_reasoning
744
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
0.00120945
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_00c4e11fa870f9ed0169ba7d2b199881968b5008afec5addcd"
is_byok
false
latency
243
model_permaslug
"openai/gpt-5.4-nano-20260317"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773829419-YujVfmr3tSBCu10TpURB"
upstream_id
"resp_00c4e11fa870f9ed0169ba7d2b199881968b5008afec5addcd"
total_cost
0.00120945
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
sentences
8
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20