NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PTH5TR9KAZXE50BTVSJJF
Run Details
Model:
GPT-5.5
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
5.8s
Cost:
$0.004675
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
9.62%
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 needled the manor windows as Inspector Vale arrived, summoned by a letter penned in trembling blue ink tonight. Inside, twelve dinner guests stood speechless around Lord Ashcombe, whose silver dessert knife protruded from his throat. The grandfather clock struck midnight twice, then stopped, as though ashamed to witness what followed in silence. Lady Ashcombe clutched her pearls, but one white glove was missing from her shaking left hand tonight. On the carpet, a trail of cigar ash curved neatly toward the locked library door behind them. Vale noticed the dead man's pocket watch still ticking, though its glass face was cracked at eleven. Then from upstairs came a child's laugh, delicate and impossible, because the nursery had burned years earlier.
created_at
"2026-04-24T21:37:36.962Z"
4/24/2026, 9:37:36 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
690
moderation_latency
(null)
generation_time
5603
tokens_prompt
46
tokens_completion
201
native_tokens_prompt
41
native_tokens_completion
149
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
0.004675
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_094eba2330ee459b0169ebe2a117cc8194bf68061f56d7e181"
is_byok
false
latency
260
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-1777066657-ncXRaQgU2jmGj8mSivBo"
session_id
(null)
api_type
"completions"
id
"gen-1777066657-7VT3YkLiKLOQFlkeZkAQ"
upstream_id
"resp_094eba2330ee459b0169ebe2a117cc8194bf68061f56d7e181"
total_cost
0.004675
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
9.62%
Matches word count
n/a
neededClean
false
sentences
7
wordCounts
0
19
1
17
2
17
3
17
4
17
5
17
6
17