NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBHJ8E4TX5D17TK2DPBE2XZ
Run Details
Model:
Qwen 3.5 122B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
1m 54s
Cost:
$0.031910
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 brass bell above the door chimed softly, cutting through the heavy scent of yeast and burnt sugar. Fine flour dusted the white counter like fresh snow. "You heard about the mayor's prize pumpkin?" "Saw the police tape myself. Tragic." "More than tragic. Someone stole the seeds. All of them." A tray of warm scones slid across the warm marble. "Blueberry? They're still fresh." "I don't want scones. I want to know who had access." "Everyone had access. The back door was unlatched." "That's what I'm afraid of." Leaning in, eyes darted toward the frosted window. "Old Silas was seen near the garden shed Tuesday night." "Silas? He hasn't left his porch since his hip went out." "Maybe he borrowed a cane. Or maybe he didn't leave at all." A coffee cup clinked against a saucer, the sound sharp in the quiet shop. "You think he's capable of sabotage?" "I think someone in this town is capable of anything if the prize money is high enough." Hands wiped on an apron, leaving a stark white streak. "Keep your head down. The pie contest starts tomorrow, and the winner gets the seed packet." "Then I suppose I better buy a ticket."
created_at
"2026-02-25T23:18:52.616Z"
2/25/2026, 11:18:52 PM
model
"qwen/qwen3.5-122b-a10b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
3324
moderation_latency
(null)
generation_time
113808
tokens_prompt
81
tokens_completion
6576
native_tokens_prompt
78
native_tokens_completion
9962
native_tokens_completion_images
(null)
native_tokens_reasoning
9672
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
0.0319096
router
(null)
provider_responses
0
endpoint_id
"33d466d1-d2f7-45ed-8ff3-fda7d2e32351"
id
"chatcmpl-2135cd1b-8bfd-9bf5-969d-4195b4bdebe2"
is_byok
false
latency
3324
model_permaslug
"qwen/qwen3.5-122b-a10b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772061532-SamaR4xWiIB0FsA3RHuO"
upstream_id
"chatcmpl-2135cd1b-8bfd-9bf5-969d-4195b4bdebe2"
total_cost
0.0319096
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)