NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PPMCR47T6X1CWWHX629XA
Run Details
Model:
GPT-5.5 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
16.1s
Cost:
$0.032005
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 stitched silver lines across Blackthorn Manor's windows while Inspector Vale arrived beneath a moonless sky, carrying unanswered telegrams tonight. Inside, the grandfather clock had stopped at midnight, though its brass pendulum still trembled like a guilty witness in darkness. Lady Morwen lay in the library, one gloved hand pointing toward the fireplace, her emerald necklace scattered nearby like tears. No servant admitted hearing screams, yet every face shone pale when Vale mentioned the locked garden door behind the pantry. A trail of muddy footprints crossed the Persian carpet, ending abruptly before the portrait of Morwen's first husband, smiling above. Vale noticed fresh ash in a crystal glass, and the faint scent of almonds hiding beneath lavender polish nearby still. When thunder shook the roof, someone upstairs laughed once, softly, and the dead woman's eyes seemed suddenly amused to Vale. Then the lights failed, leaving the inspector with darkness, breathing strangers, and one impossible question that demanded an answer tonight.
created_at
"2026-04-24T21:35:29.183Z"
4/24/2026, 9:35:29 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
15121
moderation_latency
(null)
generation_time
15930
tokens_prompt
46
tokens_completion
270
native_tokens_prompt
41
native_tokens_completion
1060
native_tokens_completion_images
0
native_tokens_reasoning
860
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
0.032005
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_055c2a63fa6c01d20169ebe221511c8194b06bdc891e94a3c8"
is_byok
false
latency
337
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-1777066529-yIR0QGVHWIansfFqVZP6"
session_id
(null)
api_type
"completions"
id
"gen-1777066529-ejn6cLUoXvJKMiZmQymb"
upstream_id
"resp_055c2a63fa6c01d20169ebe221511c8194b06bdc891e94a3c8"
total_cost
0.032005
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
8
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20