NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-25-01KMJ7S75DNBF4AH925ZG07GXA
Run Details
Model:
Qwen3 235B A22B Instruct 2507
Test:
N-Length Sentences
Scenario:
Write sentences with 20 words each
Duration:
3.2s
Cost:
$0.000033
Provider:
WandB
Evaluation summary
Score
Evaluator
Details Link
39.32%
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 steadily on the cobblestone streets of Blackthorn Manor, echoing secrets from centuries past with each droplet. Detective Eleanor Hart arrived at midnight, her trench coat damp, her mind already dissecting the silence surrounding the grand, unwelcoming estate. The butler opened the door slowly, his face pale, his trembling hands clutching a silver tray holding a single bloodstained envelope. Inside, the drawing room glowed dimly, shadows dancing across portraits of the deceased's ancestors as the clock struck one. A body lay sprawled before the fireplace, a poker protruding from the back, the carpet absorbing crimson like a hungry sponge. No footprints marred the marble hallway, no fingerprints marked the doorknobs, yet someone had clearly moved through the house like a ghost. Eleanor knelt beside the victim, noting the twisted wedding ring, the clenched jaw, and the faint scent of lavender on cold skin. The guests gathered reluctantly in the parlor, their whispers sharp, their eyes darting nervously between the detective and the closed drawing room doors. Each alibi folded neatly at first, rehearsed and polished, but cracks appeared like fractures in ancient porcelain under scrutiny. Snow began to fall outside, sealing the manor in isolation, as the murderer, calm and watching, prepared to strike again before dawn broke.
created_at
"2026-03-25T10:13:59.602Z"
3/25/2026, 10:13:59 AM
model
"qwen/qwen3-235b-a22b-07-25"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
68
moderation_latency
(null)
generation_time
3112
tokens_prompt
46
tokens_completion
351
native_tokens_prompt
44
native_tokens_completion
285
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
0.0000329
router
(null)
provider_responses
0
endpoint_id
"c9f927db-d559-49eb-9846-80862c5e3b4e"
id
"chatcmpl-854d60afdf2af48d"
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-1774433639-KhON0oFxJYckBY8KMVJb"
upstream_id
"chatcmpl-854d60afdf2af48d"
total_cost
0.0000329
cache_discount
(null)
upstream_inference_cost
0
provider_name
"WandB"
Evaluation details
Result
Evaluator
Details
Meta Data
39.32%
Matches word count
n/a
neededClean
false
sentences
10
wordCounts
0
19
1
21
2
21
3
19
4
21
5
22
6
22
7
23
8
19
9
23