NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0NT28Z7S28R7KKS0RJC4W3
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
12.9s
Cost:
$0.019885
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 10 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
Rain polished the courthouse steps when Inspector Vale found blood. It shimmered beneath lamplight, leading toward the locked records office. Inside, Judge Marlowe sat upright, smiling despite the bullet wound. His gavel rested neatly beside a glass of untouched brandy. On the desk, one torn verdict burned without any flame. The office door remained bolted from within, impossibly secure tonight. Vale noticed mud on the windowsill, though windows were sealed. A clock chimed thirteen, then stopped before finishing midnight properly. Outside, the jurors waited, whispering names they feared speaking aloud. Vale pocketed a silver cufflink engraved with his own initials.
created_at
"2026-04-24T21:19:53.128Z"
4/24/2026, 9:19:53 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
11812
moderation_latency
(null)
generation_time
12135
tokens_prompt
46
tokens_completion
604
native_tokens_prompt
41
native_tokens_completion
656
native_tokens_completion_images
0
native_tokens_reasoning
516
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
0.019885
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0e2327ff754f1f500169ebde793a2c81969ae0e258319e2f4a"
is_byok
false
latency
257
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-1777065593-Vijjqq3TpLppMP7Yy5QX"
session_id
(null)
api_type
"completions"
id
"gen-1777065593-MT9BHWfPBnjyvCkpzUSJ"
upstream_id
"resp_0e2327ff754f1f500169ebde793a2c81969ae0e258319e2f4a"
total_cost
0.019885
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
10
1
10
2
10
3
10
4
10
5
10
6
10
7
10
8
10
9
10