NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-24-01KQ01ZEC5C95DH441ED4GCZZY
Run Details
Model:
GPT-OSS 120B
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
7.7s
Cost:
$0.000747
Provider:
Amazon Bedrock
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 hammered the slate roof, drowning the quiet manor as yet another thunderous night settled ominously over the distant hills. Inside, the grand foyer glimmered with candlelight, shadows dancing across portraits that seemed to watch every uneasy guest in silence. Detective Marlowe arrived, trench coat dripping, eyes scanning the marble floor for clues hidden beneath polished elegance of the night. A sudden scream shattered the hush, echoing through corridors, and a lifeless body lay sprawled near the crystal staircase tonight. Marlowe knelt, noticing a silver locket clutched in trembling fingers, its picture fractured, revealing a suspect's unmistakable grin of danger.
created_at
"2026-04-24T15:33:17.841Z"
4/24/2026, 3:33:17 PM
model
"openai/gpt-oss-120b"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
6659
moderation_latency
341
generation_time
6974
tokens_prompt
46
tokens_completion
1272
native_tokens_prompt
102
native_tokens_completion
1219
native_tokens_completion_images
(null)
native_tokens_reasoning
1097
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
"end_turn"
usage
0.0007467
router
(null)
provider_responses
0
endpoint_id
"8b516897-c13e-4925-afc3-44fa86608fe9"
is_byok
false
latency
340
model_permaslug
"openai/gpt-oss-120b"
provider_name
"AtlasCloud"
status
429
1
endpoint_id
"b3f80c05-e31a-44f6-b63f-414467b87553"
id
"e37bb50b-c4c9-408b-a2d6-db154dacfbf3"
is_byok
false
latency
1454
model_permaslug
"openai/gpt-oss-120b"
provider_name
"Amazon Bedrock"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777044797-RXdzpqX4SSDQZYbjLAaE"
session_id
(null)
api_type
"completions"
id
"gen-1777044797-VLskLm74cK7anqvQ7ZPq"
upstream_id
"e37bb50b-c4c9-408b-a2d6-db154dacfbf3"
total_cost
0.0007467
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Amazon Bedrock"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
sentences
5
wordCounts
0
20
1
20
2
20
3
20
4
20