NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM096QQ5SFSRNF2EHZK1RMRK
Run Details
Model:
GPT-5.4 Nano
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
2.0s
Cost:
$0.000209
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
11.08%
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
Detective Mara Venn arrived at Alderwick Station, where rain fell steadily and passengers whispered around a silent body. The victim lay beside the locked luggage office, one glove missing, while constable Holt guarded the warped doorframe carefully. Inspector Kellan insisted it was theft gone wrong, yet the brass keyhole gleamed oddly under lantern light. Mara noticed fresh bootprints ending abruptly at puddles, then continuing as faint streaks toward river reeds. A conductor swore he heard arguing at midnight, and then a single scream dissolved into locomotive hiss. On the platform, a violin case sat untouched, despite frost, its clasp engraved with the letter A. Mara asked for the timetable ledger, and Holt produced it, trembling like paper near flame.
created_at
"2026-03-18T10:52:31.348Z"
3/18/2026, 10:52:31 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1123
moderation_latency
(null)
generation_time
1907
tokens_prompt
46
tokens_completion
199
native_tokens_prompt
41
native_tokens_completion
161
native_tokens_completion_images
0
native_tokens_reasoning
0
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
0.00020945
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_02b8f1012d0c59b90169ba83ef6acc8190ad379a86eabece8a"
is_byok
false
latency
221
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-1773831151-PTeMxvC5njPwWUsaXHv4"
upstream_id
"resp_02b8f1012d0c59b90169ba83ef6acc8190ad379a86eabece8a"
total_cost
0.00020945
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
11.08%
Matches word count
n/a
neededClean
false
sentences
7
wordCounts
0
18
1
19
2
17
3
16
4
17
5
17
6
15