NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ8RFJXPH4PGH02EWFX2C05
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
3.5s
Cost:
$0.000029
Provider:
WandB
Evaluation summary
Score
Evaluator
Details Link
31.13%
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
The rain fell in steady sheets, drenching the cobblestones beneath the flickering gaslight of the quiet street. Detective Alden stepped from his carriage, coat pulled tight, eyes scanning the shadowed townhouse with practiced suspicion. Footsteps echoed behind him—Inspector Greaves, breath visible, hand resting cautiously near his hidden revolver. The front door stood ajar, revealing darkness within, faintly illuminated by a single trembling candle upstairs. A maid knelt by the threshold, shivering, clutching a silver locket she claimed she found near the body. No one had heard the scream, the neighbors said, though the walls were thin and nights always noisy. The victim lay sprawled across the library rug, silk robe stained crimson, a poker lodged in the floor beside him. His watch had stopped at eleven, but the clock on the mantel read half past twelve with unwavering precision. A half-written letter sat on the desk, addressed to “My Dearest Evelyn,” words ending abruptly in a smudged blot. The window latch was broken, yet nothing was stolen, and the footprints outside led only in one direction—away.
created_at
"2026-03-25T10:31:04.033Z"
3/25/2026, 10:31:04 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
80
moderation_latency
(null)
generation_time
3348
tokens_prompt
46
tokens_completion
294
native_tokens_prompt
44
native_tokens_completion
246
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
0.000029
router
(null)
provider_responses
0
endpoint_id
"043eb28f-fc28-4b0d-9800-b249fcfcfbf9"
is_byok
false
latency
8
model_permaslug
"qwen/qwen3-235b-a22b-07-25"
provider_name
"Parasail"
status
429
1
endpoint_id
"c9f927db-d559-49eb-9846-80862c5e3b4e"
id
"chatcmpl-bc029483d92ea064"
is_byok
false
latency
33
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-1774434664-laPd15UR5qsYCXeppnK0"
upstream_id
"chatcmpl-bc029483d92ea064"
total_cost
0.000029
cache_discount
(null)
upstream_inference_cost
0
provider_name
"WandB"
Evaluation details
Result
Evaluator
Details
Meta Data
31.13%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
17
1
17
2
15
3
16
4
18
5
18
6
20
7
19
8
19
9
19