NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PEB3VYMP2BZHY66FE6KMR
Run Details
Model:
GPT-5.5
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
5.6s
Cost:
$0.004735
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
2.42%
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 threads across Blackthorn Hall, while Inspector Vale counted ten dinner guests and one empty chair. At midnight, the grandfather clock coughed once, then stopped, leaving the house breathing like a buried animal. Lady Marwick laughed too loudly, raising her glass toward portraits that watched with varnished, accusing, patient eyes. In the library, a fire collapsed, revealing mud on the carpet and blood beneath the desk. Vale found Sir Edmund face-down beside an overturned chessboard, a black queen clenched between his stiff fingers. No window stood open, no servant had screamed, and every key remained inside its proper lock. Yet the dead man’s watch ticked steadily backward, marking minutes none of the living remembered spending.
created_at
"2026-04-24T21:30:57.55Z"
4/24/2026, 9:30:57 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2393
moderation_latency
(null)
generation_time
5417
tokens_prompt
46
tokens_completion
196
native_tokens_prompt
41
native_tokens_completion
151
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
0.004735
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_026604a63c8dbdd10169ebe111b7888193ba6fe586620c1233"
is_byok
false
latency
376
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-1777066257-dem0Of4oTuL3tVvZRRsz"
session_id
(null)
api_type
"completions"
id
"gen-1777066257-2NjYF4JRqGpbgqXCXYm6"
upstream_id
"resp_026604a63c8dbdd10169ebe111b7888193ba6fe586620c1233"
total_cost
0.004735
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
2.42%
Matches word count
n/a
neededClean
false
sentences
7
wordCounts
0
18
1
17
2
17
3
16
4
17
5
16
6
16