NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ0PWTHTGA9R3BGMG1JFD0M4
Run Details
Model:
GPT-5.5 (Reasoning, Low)
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
14.2s
Cost:
$0.028315
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 stitched silver threads across Blackthorn Manor as Inspector Vale arrived, finding the front doors yawning open like accusations tonight. Inside, the grandfather clock had stopped at midnight, though its pendulum still trembled faintly behind cracked glass in the hall. Lady Marwick lay beneath the chandelier, pearls scattered around her throat like moons escaped from a broken sky above her. Beside her hand rested a playing card, the queen of spades, soaked dark along one corner with fresh red blood. Vale noticed four muddy footprints crossing the marble, each pointing inward, none returning toward the rain outside the doors again. From the library, someone whispered a prayer, then silenced themselves when Vale lifted his lantern toward the voice in warning. The household servants waited on the staircase, pale as laundry, insisting their mistress had hosted no guests after supper ended. Yet twelve wet umbrellas crowded the stand, and one still dripped beside a gentleman's monogrammed cane near the mirror quietly.
created_at
"2026-04-24T21:38:52.1Z"
4/24/2026, 9:38:52 PM
model
"openai/gpt-5.5-20260423"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
12954
moderation_latency
(null)
generation_time
14040
tokens_prompt
46
tokens_completion
530
native_tokens_prompt
41
native_tokens_completion
937
native_tokens_completion_images
0
native_tokens_reasoning
737
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
0.028315
router
(null)
provider_responses
0
endpoint_id
"58e5b336-423e-430b-a2ab-8bc353f0c51b"
id
"resp_0d2bb9e64c37b2640169ebe2ec2de0819488ededba07d6e159"
is_byok
false
latency
323
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-1777066732-8AVFMHAwJGhxuMbeYh4l"
session_id
(null)
api_type
"completions"
id
"gen-1777066732-WWtZB2RyR4OzBlCxjqtl"
upstream_id
"resp_0d2bb9e64c37b2640169ebe2ec2de0819488ededba07d6e159"
total_cost
0.028315
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