NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-09-01KK9Q9SA2ST03726BM1RYNSW0
Run Details
Model:
GPT-5.4 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
28.7s
Cost:
$0.027807
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
Rain polished manor windows while Inspector Vale arrived, summoned before dawn by a voice trembling around one impossible word: murder. Inside, candles guttered in silver sconces, and the household waited along the corridor like mourners rehearsing grief before confirmation arrived. Lady Winter stood nearest the library door, her pearl necklace broken, white beads scattered like tiny alibis across the carpet. On the Persian rug beyond her slippered feet, Augustus Blackwell lay smiling faintly, a letter opener planted beneath his ribs. The clock above the mantel showed six, yet nobody flinched, because it had stopped hours earlier, exactly at midnight sharp. Vale removed his gloves, noting mud on the sill, perfume in the smoke, and one guest carefully avoiding Augustus entirely.
created_at
"2026-03-09T16:36:19.404Z"
3/9/2026, 4:36:19 PM
model
"openai/gpt-5.4-20260305"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
28157
moderation_latency
(null)
generation_time
28510
tokens_prompt
46
tokens_completion
730
native_tokens_prompt
41
native_tokens_completion
1847
native_tokens_completion_images
0
native_tokens_reasoning
1690
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
0.0278075
router
(null)
provider_responses
0
endpoint_id
"9ff5625c-403f-4d7f-b895-58ac7295062c"
id
"resp_0dbe8441616391d00169aef7037f44819594c1da35660bd50b"
is_byok
false
latency
206
model_permaslug
"openai/gpt-5.4-20260305"
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-1773074179-JU4se9BurFMhZYrNra9K"
upstream_id
"resp_0dbe8441616391d00169aef7037f44819594c1da35660bd50b"
total_cost
0.0278075
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
6
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20