NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0P59S2APD7EX8K9BD58VJJ
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
19.4s
Cost:
$0.038665
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 worried the windows of Blackthorn Manor while seven guests waited for midnight and pretended not to hear thunder outside. In the library, candles trembled beside portraits whose painted eyes seemed freshly accused by every violent flash of lightning outside. Detective Mara Vale arrived late, her coat dripping dark water onto the tiles like evidence refusing to dry before morning. Lord Ashcombe's chair stood empty at the head of dinner, though his wineglass still held a single ruby mouthful untouched. No one mentioned the locked study upstairs, or the bell that had rung twice after servants withdrew for the night. Mara noticed mud on the Persian carpet, shaped by a boot too large for any lady present in the room. Sir Julian laughed first, too loudly, and asked whether detectives usually counted footprints before greeting their hosts at dinner parties. Before Mara answered, a scream unfurled above them, long and silver, from behind the study door on the landing overhead. They found Lord Ashcombe seated at his desk, smiling faintly, with an ivory letter opener in his throat before dawn. On the blotter, in drying ink, he had written only one word: forgive, underlined with blood and an unmistakable flourish.
created_at
"2026-04-24T21:26:01.259Z"
4/24/2026, 9:26:01 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
17984
moderation_latency
(null)
generation_time
18720
tokens_prompt
46
tokens_completion
831
native_tokens_prompt
41
native_tokens_completion
1282
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"
usage
0.038665
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_081dbed39fcc99200169ebdfe955fc81978615bddffbadc7dc"
is_byok
false
latency
248
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-1777065961-aylOybD8OH7vH7mB2IDK"
session_id
(null)
api_type
"completions"
id
"gen-1777065961-R2vjSLPUFlQbtXZ96co0"
upstream_id
"resp_081dbed39fcc99200169ebdfe955fc81978615bddffbadc7dc"
total_cost
0.038665
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20
8
20
9
20