NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PC0A5M0T5F3NMFP50B7PW
Run Details
Model:
GPT-5.5
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
4.5s
Cost:
$0.003835
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
59.10%
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 polished the manor windows while Inspector Vale arrived, counting thirteen candles and one chair turned toward the locked study. Inside, Lord Aster lay beneath scattered chessmen, his silver cufflink missing, and the grandfather clock stopped at midnight precisely. No one admitted hearing screams, though the guests stood pale and silent, each clutching secrets like knives under velvet. Vale noticed wet footprints crossing the Persian rug, beginning at the corpse and ending before a bookcase without handles. Then the widow laughed softly upstairs, and every candle in the hall extinguished at once, except the thirteenth.
created_at
"2026-04-24T21:29:40.994Z"
4/24/2026, 9:29:40 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
665
moderation_latency
(null)
generation_time
4409
tokens_prompt
46
tokens_completion
161
native_tokens_prompt
41
native_tokens_completion
121
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
0.003835
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_000486e759e7ed1b0169ebe0c513b881969b13d2f10ed203f8"
is_byok
false
latency
420
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-1777066180-09Z91bFGvMkMKGmo5aFY"
session_id
(null)
api_type
"completions"
id
"gen-1777066180-xl5BFzXvONhy5SQ4BSxp"
upstream_id
"resp_000486e759e7ed1b0169ebe0c513b881969b13d2f10ed203f8"
total_cost
0.003835
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
59.10%
Matches word count
n/a
neededClean
false
sentences
5
wordCounts
0
20
1
19
2
19
3
19
4
18