NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-23-01M37J0366DD6A1BBR6NF36XAT
Run Details
Model:
GPT-6 Sol (Reasoning, Medium)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
18.0s
Cost:
$0.012612
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
95.63%
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, the lighthouse keeper found a corpse beneath the stairs, although the island's only boat remained securely chained ashore. The dead man wore the mayor's coat, but his face belonged to someone who had been buried only last Tuesday. Inspector Mara Voss arrived with the tide, carrying a warrant, a lantern, and a letter addressed in her mother's handwriting. Her mother had died twenty years earlier, in that same lighthouse, behind a door nobody had ever managed to unlock. Now the door stood open, and wet footprints led from its threshold to the dead man's outstretched, accusing hand. In his fist lay a brass key, still warm, though the keeper swore he had touched nothing since discovering him. Mara turned the letter over and saw one sentence: Do not trust the person who tells you I am dead. Behind her, the keeper whispered that he had heard three sharp knocks upstairs, where the locked room held no windows. Then the bell rang once, and Mara noticed blood dripping steadily from the clapper, though nobody had recently climbed above.
created_at
"2026-09-23T16:36:19.278Z"
9/23/2026, 4:36:19 PM
model
"openai/gpt-6-sol-20260922"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
16823
moderation_latency
(null)
generation_time
17920
tokens_prompt
46
tokens_completion
372
native_tokens_prompt
41
native_tokens_completion
1253
native_tokens_completion_images
0
native_tokens_reasoning
1034
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
service_tier
"default"
usage
0.012612
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.20.0; linux; x64))"
http_referer
(null)
request_id
"req-1790181379-Axkx2NJz3wHofIMg9Iir"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1790181379-sSzcx6h9Hm7OF8Io49i1"
upstream_id
"resp_0f8ac82141e19a9a016ab40003652087d19b995df3e17731fd"
provider_responses
0
endpoint_id
"1cfc7d9d-4404-4b8e-9ee4-58ae45c9dcd4"
id
"resp_0f8ac82141e19a9a016ab40003652087d19b995df3e17731fd"
is_byok
false
latency
1081
model_permaslug
"openai/gpt-6-sol-20260922"
provider_name
"OpenAI"
status
200
total_cost
0.012612
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
95.63%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
20
1
20
2
20
3
20
4
19
5
20
6
20
7
20
8
20