NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0P52CY8HZ9SHWND20E0Y93
Run Details
Model:
GPT-5.5
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
5.2s
Cost:
$0.003715
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
30.83%
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 needled the windows of Blackthorn Manor while nine strangers waited for midnight in the candlelit drawing room upstairs tonight. Detective Mara Vale noticed the grandfather clock had stopped, though its brass pendulum still swung in perfect silence. Lord Eversham smiled at everyone, lifted his crystal glass, and collapsed before the first toast was finished there. The scream came from his widow, but Mara watched the butler pocket something silver with trembling gloved hands. Outside, thunder swallowed the telephone’s final ring, and every door in the old house locked by itself simultaneously.
created_at
"2026-04-24T21:25:53.702Z"
4/24/2026, 9:25:53 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2437
moderation_latency
(null)
generation_time
5024
tokens_prompt
46
tokens_completion
159
native_tokens_prompt
41
native_tokens_completion
117
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
0.003715
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0e7e72b0f479b8e40169ebdfe20c5c8196a10a47459e422e7b"
is_byok
false
latency
589
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-1777065953-GOcZyN5DJU8UkaId4SER"
session_id
(null)
api_type
"completions"
id
"gen-1777065953-IMAiSXLg8zaJEeKskgWv"
upstream_id
"resp_0e7e72b0f479b8e40169ebdfe20c5c8196a10a47459e422e7b"
total_cost
0.003715
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
30.83%
Matches word count
n/a
neededClean
false
sentences
5
wordCounts
0
20
1
18
2
18
3
18
4
18