NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0N788MNRENG5D5446XJM77
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
12.0s
Cost:
$0.019285
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 lashed Blackwater Manor as midnight swallowed the coastal village. Inside, twelve guests waited beside a fire burning unnaturally blue. Lord Ashcombe raised his glass, smiled, then collapsed without sound. The crystal shattered, scattering wine like blood across marble tiles. Someone screamed, and every candle in the hall went out. When light returned, the butler stood beside the locked doors. His white gloves were spotless, except for one crimson fingerprint. Detective Mara Venn noticed the dead man's watch still ticking. It was set three hours ahead of the present hour.
created_at
"2026-04-24T21:09:36.669Z"
4/24/2026, 9:09:36 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
11573
moderation_latency
(null)
generation_time
11810
tokens_prompt
46
tokens_completion
401
native_tokens_prompt
41
native_tokens_completion
636
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
0.019285
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0b36c509c88bb55f0169ebdc10c4d0819594379d6f62c81a9d"
is_byok
false
latency
240
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-1777064976-KZxnfbmc9nYGGe6aZSZ2"
session_id
(null)
api_type
"completions"
id
"gen-1777064976-anefk53YvnzsV2Q3LAN9"
upstream_id
"resp_0b36c509c88bb55f0169ebdc10c4d0819594379d6f62c81a9d"
total_cost
0.019285
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
9
wordCounts
0
10
1
10
2
10
3
10
4
10
5
10
6
10
7
10
8
10