NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBDVHD44VNZRP9584ADRK1N
Run Details
Model:
Qwen 3.5 122B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
28.6s
Cost:
$0.015158
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The scent of burnt sugar clung to the air, mixing with the sharp morning chill drifting through the open door. The bell above the door remained silent, the shop locked against the world. "You shouldn't have opened the safe." "It was unlocked. It was practically begging." "And now the whole town knows about the ledger." "They know because you told them." "I told them nothing. I just saw the police car parked outside." Flour dusted the wooden counter like fresh snow. A heavy rolling pin was set down with a definitive thud. "Did you see the entry for Tuesday?" "I saw the withdrawal." "Two thousand dollars. Gone." "Gone where?" "Into the bakery's accounts. But not for ingredients." Silence stretched between them, heavy as the cast iron pans hanging overhead. "Are you saying I embezzled?" "I'm saying the money matches the missing funds from the library." "That's impossible." "Is it? Or is it just inconvenient?" The espresso machine hissed violently, filling the sudden void. "Then we have a problem." "We already had a problem. Now we have a suspect." "Not yet." "Soon." A hand reached for the leather-bound ledger. "Put that down." "I'm just checking the math." "For the police report." "Or for the alibi."
created_at
"2026-02-25T22:14:02.412Z"
2/25/2026, 10:14:02 PM
model
"qwen/qwen3.5-122b-a10b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
441
moderation_latency
(null)
generation_time
28536
tokens_prompt
81
tokens_completion
4230
native_tokens_prompt
78
native_tokens_completion
4727
native_tokens_completion_images
(null)
native_tokens_reasoning
4427
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
0.0151576
router
(null)
provider_responses
0
endpoint_id
"33d466d1-d2f7-45ed-8ff3-fda7d2e32351"
id
"chatcmpl-faab927d-5e66-9c14-959e-e1f9eff825ff"
is_byok
false
latency
437
model_permaslug
"qwen/qwen3.5-122b-a10b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772057642-596BpVDr89cVCvFhWkZu"
upstream_id
"chatcmpl-faab927d-5e66-9c14-959e-e1f9eff825ff"
total_cost
0.0151576
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)