NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0N0WJ1E3V74XGJNEEXB01Q
Run Details
Model:
GPT-5.5 (Reasoning)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
19.2s
Cost:
$0.037975
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
At midnight, Blackthorn Manor shuddered beneath rain while Detective Mara Vale arrived, summoned by a bell no living hand rang. The butler opened the door silently, his gloves stained with candle wax and something darker along the trembling seams tonight. Inside, guests clustered near the grand staircase, whispering over brandy glasses as thunder erased every confession before it surfaced properly. Lord Blackthorn lay in the library, one eye open, a silver letter knife flowering from his chest like winter roses. Mara noticed the fire had died, though the poker glowed red beside a puddle spreading toward the hearth's stone tiles. On the desk, a stopped clock pointed to twelve, but its glass was warm beneath her fingertip when touched gently. Beside it, an unsigned note promised vengeance before dawn, written in ink smelling faintly of almonds and bitter smoke tonight. When Mara asked who found him first, every face turned toward the portrait hanging above the corpse in silence together. The painted ancestor smiled thinly, and from behind its frame came one final, impossible drop of blood onto silk wallpaper.
created_at
"2026-04-24T21:06:08.074Z"
4/24/2026, 9:06:08 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
18340
moderation_latency
(null)
generation_time
19061
tokens_prompt
46
tokens_completion
692
native_tokens_prompt
41
native_tokens_completion
1259
native_tokens_completion_images
0
native_tokens_reasoning
1034
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
0.037975
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_034fa5069ecd7daf0169ebdb4033bc8196955f62cfe414a76c"
is_byok
false
latency
332
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-1777064768-4K4wDldD6BV4I68sffc5"
session_id
(null)
api_type
"completions"
id
"gen-1777064768-NaDQd0IOx5zxvGsgma02"
upstream_id
"resp_034fa5069ecd7daf0169ebdb4033bc8196955f62cfe414a76c"
total_cost
0.037975
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
9
wordCounts
0
20
1
20
2
20
3
20
4
20
5
20
6
20
7
20
8
20