NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PKJEMX4FG2DJMPNNZ1Y0J
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
19.9s
Cost:
$0.052705
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 hammered the stained glass roof as Inspector Vale arrived at Blackthorn Hall before the dinner bell stopped trembling tonight. Inside, twelve guests stood frozen around Lord Ashcombe, whose white shirt bloomed red beneath the gleaming silver ceremonial carving knife. The candles guttered when thunder rolled, and every shadow seemed to step closer to the body on the parquet floor. Vale removed his gloves, noticed bloodless fingertips, and asked who had touched the knife since the scream in the library. No one answered, but Lady Ashcombe laughed once, softly, as if hearing a private joke from beyond the grave itself. At her feet, a broken pocket watch ticked backward, though its hands were smeared with clotted blood and black ash. Vale knelt beside it and saw an engraving scratched fresh across the case: Remember the drowned girl beneath the pier. Before he could rise, the lights failed, and another guest whispered his name in the dark with terrible certainty nearby.
created_at
"2026-04-24T21:33:48.907Z"
4/24/2026, 9:33:48 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
18645
moderation_latency
(null)
generation_time
19705
tokens_prompt
46
tokens_completion
259
native_tokens_prompt
41
native_tokens_completion
1750
native_tokens_completion_images
0
native_tokens_reasoning
1552
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
0.052705
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_00d1b0a7ad0fe9e70169ebe1bcfc108190956d7ef98d20abbe"
is_byok
false
latency
273
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-1777066428-j6TeRnQePYLwiEFkv8BN"
session_id
(null)
api_type
"completions"
id
"gen-1777066428-iSGbYWbVcuMdjdLabpjx"
upstream_id
"resp_00d1b0a7ad0fe9e70169ebe1bcfc108190956d7ef98d20abbe"
total_cost
0.052705
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