NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0NYA4XS5ED3K0EPBP0Y5QS
Run Details
Model:
GPT-5.5
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
4.4s
Cost:
$0.003775
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
17.99%
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 stitched silver threads across Blackmoor Station as Inspector Vale stepped from the train into fog smelling of coal. At midnight, the manor’s windows glowed ahead, though Lord Ashbury’s telegram had requested help tomorrow, not tonight. The butler met him by the gates, pale, gloved hands trembling around a lantern with cracked yellow glass. “Inspector,” he whispered, “forgive the hour, but someone has murdered Lady Ashbury inside the locked music room.” From the house came one piano note, soft and deliberate, though every servant stood waiting outside in terror.
created_at
"2026-04-24T21:22:12.261Z"
4/24/2026, 9:22:12 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
615
moderation_latency
(null)
generation_time
4287
tokens_prompt
46
tokens_completion
155
native_tokens_prompt
41
native_tokens_completion
119
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)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"completed"
usage
0.003775
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_04d0e0f9337335e20169ebdf0460e081948f9db8c7665d36a9"
is_byok
false
latency
285
model_permaslug
"openai/gpt-5.5-20260423"
provider_name
"OpenAI"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777065732-o8L62Mv7GlZ7cGuXysG7"
session_id
(null)
api_type
"completions"
id
"gen-1777065732-lnT98ZHFtHFIfScPE2XH"
upstream_id
"resp_04d0e0f9337335e20169ebdf0460e081948f9db8c7665d36a9"
total_cost
0.003775
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
17.99%
Matches word count
n/a
neededClean
false
sentences
5
wordCounts
0
19
1
17
2
18
3
17
4
18