NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ88B8F6FZ7E3SQKX3ARDY5
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
N-Length Sentences
Scenario:
Write sentences with 10 words each
Duration:
3.0s
Cost:
$0.000133
Provider:
Friendli
Evaluation summary
Score
Evaluator
Details Link
85.24%
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
Rain poured heavily as midnight struck the old hillside mansion. A lone figure stumbled through the garden, clutching a bloodied pocket watch. Thunder cracked loudly, silhouetting the man collapsing near the rose bushes. His final breath formed mist in the frigid, unforgiving night air. Upstairs, a clock stopped abruptly, hands frozen at twelve-ten sharp. No one heard the soft click of the study door unlocking. Candles flickered once, revealing a portrait with strangely hollow eyes. A letter lay sealed on the desk beside cold tea. Outside, a raven shrieked, vanishing into the storm-racked sky entirely. Morning brought police, silence, and one unexplained footprint leading nowhere.
created_at
"2026-03-25T10:22:15.315Z"
3/25/2026, 10:22:15 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
142
moderation_latency
(null)
generation_time
2924
tokens_prompt
46
tokens_completion
184
native_tokens_prompt
44
native_tokens_completion
155
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
0.0001328
router
(null)
provider_responses
0
endpoint_id
"02b90f2a-e684-46b3-808b-eb88e1348e29"
id
"chatcmpl-19b67ce23b4841a5a2a0201d909d494e"
is_byok
false
latency
142
model_permaslug
"qwen/qwen3-235b-a22b-07-25"
provider_name
"Friendli"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1774434135-7ktxAVets9IvorKB0Ajx"
upstream_id
"chatcmpl-19b67ce23b4841a5a2a0201d909d494e"
total_cost
0.0001328
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Friendli"
Evaluation details
Result
Evaluator
Details
Meta Data
85.24%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
10
1
12
2
11
3
11
4
10
5
11
6
10
7
10
8
10
9
10