NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-18-01KM0ASK1NVWRT0Z2NEB6R4680
Run Details
Model:
GPT-5.4 Nano (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
10.6s
Cost:
$0.001016
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
85.59%
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
At midnight, rain stitched the manor windows, and Detective Lark arrived to investigate a silent, crimson-scarred corpse in its study. The housekeeper whispered that Sir Alden never entertained strangers, yet the front door showed fresh bootmarks leading inward, then vanishing. Inside, lanternlight pooled around a shattered clock, stopped precisely when the alarm bell finally rang for the third floor study. Lark noted dried rosewater on the victim's cuffs, and a wax seal bearing unfamiliar initials underneath the overturned leather blotter. Suspects gathered in the corridor—maid, nephew, accountant—each reciting alibis with practiced, anxious smiles while stormwind worried tapestries and candles flickered. When Lark lifted the seal, a faint scent of smoke rose, implying someone burned documents nearby to erase last proof.
created_at
"2026-03-18T11:20:17.729Z"
3/18/2026, 11:20:17 AM
model
"openai/gpt-5.4-nano-20260317"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
9993
moderation_latency
(null)
generation_time
10115
tokens_prompt
46
tokens_completion
715
native_tokens_prompt
41
native_tokens_completion
806
native_tokens_completion_images
0
native_tokens_reasoning
631
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
0.0010157
router
(null)
provider_responses
0
endpoint_id
"0c835f2e-c18d-4e8c-b245-e1e3bd08b97f"
id
"resp_0e5a9418918446780169ba8a71c678819585c3022977e883b0"
is_byok
false
latency
169
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-1773832817-pIzHvchR4P8bYsKEhkJX"
upstream_id
"resp_0e5a9418918446780169ba8a71c678819585c3022977e883b0"
total_cost
0.0010157
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
Evaluation details
Result
Evaluator
Details
Meta Data
85.59%
Matches word count
n/a
neededClean
false
sentences
6
wordCounts
0
20
1
20
2
20
3
20
4
22
5
20