NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0P0NRCSP81DQXFJ87Y3DHC
Run Details
Model:
GPT-5.5 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
14.8s
Cost:
$0.027715
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 combed the windows of Blackthorn Manor while Inspector Vale arrived late, carrying a letter sealed with crimson wax tonight. Inside, the grandfather clock had stopped at midnight, though every guest insisted dinner ended before eleven exactly that stormy evening. Lord Ashbury lay beneath the portrait gallery, one hand clenched around a chess knight carved from bone and blackened silver. No blood marked his waistcoat, yet the scent of bitter almonds lingered above the polished parquet like accusation itself there. Lady Maren watched from the staircase, her pearls trembling softly against skin too pale for grief or innocence tonight either. The butler claimed the library door was locked, but Vale noticed fresh mud on the threshold beside the latch inside. Somewhere upstairs, a floorboard groaned, and seven frightened faces turned toward the darkness above as thunder answered sharply outside again. Vale broke the seal, unfolded the letter, and read the dead man's final invitation aloud to everyone waiting there nearby.
created_at
"2026-04-24T21:23:29.685Z"
4/24/2026, 9:23:29 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
13644
moderation_latency
(null)
generation_time
13770
tokens_prompt
46
tokens_completion
673
native_tokens_prompt
41
native_tokens_completion
917
native_tokens_completion_images
0
native_tokens_reasoning
719
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
0.027715
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_00b1dce34574cc240169ebdf51c41c8194b4dfff57cd8bd943"
is_byok
false
latency
345
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-1777065809-Y0jvBeYcqRT5gDrlOdFh"
session_id
(null)
api_type
"completions"
id
"gen-1777065809-WNdSl2XRxail9L7E4Mhk"
upstream_id
"resp_00b1dce34574cc240169ebdf51c41c8194b4dfff57cd8bd943"
total_cost
0.027715
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