NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0P5TKR9SZBQ3B71R730FMM
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
17.0s
Cost:
$0.035545
Provider:
OpenAI
Evaluation summary
Score
Evaluator
Details Link
95.63%
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 glass roof of Blackthorn Station as Inspector Vale arrived, summoned by a telegram without signature tonight alone. Inside, the midnight train stood steaming, its first class carriage locked, curtains drawn, and every brass handle wiped perfectly clean. The stationmaster waited beneath the clock, twisting his cap, while a porter sobbed silently beside abandoned trunks near platform seven alone. Vale saw the blood first, a narrow ribbon escaping beneath the compartment door and darkening the polished floorboards like ink. No passenger admitted knowing the victim, though six held tickets purchased together under a name nobody recognized at the office. From within the sealed carriage came a woman's laugh, soft, impossible, and followed immediately by three deliberate knocks against wood. Vale ordered silence, raised his lantern, and noticed snow melting across the threshold, though no snow had fallen that week. When the key turned finally, the door opened inward upon Lord Harbury, dead, smiling, and clutching a violet between fingers. Pinned to his lapel was a card reading, Vale, forgive me, but tonight you must suspect everyone, including the dead.
created_at
"2026-04-24T21:26:18.496Z"
4/24/2026, 9:26:18 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
15829
moderation_latency
(null)
generation_time
16852
tokens_prompt
46
tokens_completion
310
native_tokens_prompt
41
native_tokens_completion
1178
native_tokens_completion_images
0
native_tokens_reasoning
951
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
0.035545
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_04b154aa93d78c970169ebdffa8ff8819686142ef87a4a8f01"
is_byok
false
latency
232
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-1777065978-GiXhUqySi7cKfxwpDCnG"
session_id
(null)
api_type
"completions"
id
"gen-1777065978-4t6GQDPZTjd1i39UMlbO"
upstream_id
"resp_04b154aa93d78c970169ebdffa8ff8819686142ef87a4a8f01"
total_cost
0.035545
cache_discount
(null)
upstream_inference_cost
0
provider_name
"OpenAI"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
95.63%
Matches word count
n/a
neededClean
false
sentences
9
wordCounts
0
20
1
20
2
21
3
20
4
20
5
20
6
20
7
20
8
20