NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ88AFZT9F9PDZNH86WDYXV
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
1.5s
Cost:
$0.000017
Provider:
WandB
Evaluation summary
Score
Evaluator
Details Link
79.27%
Matches word count
(details)
Model input
User/Human
Please write the opening scene of a murder mystery where each sentence has exactly 10 words. Please make sure that each sentence has the same length. Only return the opening itself.
Model response
Messages
Meta
AI
The rain fell hard on the silent, sleeping town. Clock struck midnight as the mansion’s lights blinked out. Footsteps crunched gravel leading toward the shadowed, back entrance. A scream tore through the wind, then stopped abruptly. Police car skidded sideways across the wet, cracked driveway. Detective Cole stepped out, coat pulled tight against chill. Blood dripped slowly from the broken, shattered front window. He drew his flashlight, its beam cutting through dark mist. Portrait swung open, revealing a hidden room behind it. A single note lay folded beside the cold, pale hand.
created_at
"2026-03-25T10:22:14.531Z"
3/25/2026, 10:22:14 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
69
moderation_latency
(null)
generation_time
1432
tokens_prompt
46
tokens_completion
159
native_tokens_prompt
44
native_tokens_completion
129
native_tokens_completion_images
(null)
native_tokens_reasoning
0
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0000173
router
(null)
provider_responses
0
endpoint_id
"c9f927db-d559-49eb-9846-80862c5e3b4e"
id
"chatcmpl-815feb2f73b35424"
is_byok
false
latency
39
model_permaslug
"qwen/qwen3-235b-a22b-07-25"
provider_name
"WandB"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774434134-tJXH1Ja1CArVIjE0Ic1Z"
upstream_id
"chatcmpl-815feb2f73b35424"
total_cost
0.0000173
cache_discount
(null)
upstream_inference_cost
0
provider_name
"WandB"
Evaluation details
Result
Evaluator
Details
Meta Data
79.27%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
9
1
9
2
9
3
9
4
9
5
9
6
9
7
10
8
9
9
10