NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ6ZXTASZ9MT5BWFYE4WEYZC
Run Details
Model:
Qwen 3.5 Plus (2026-04-20)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
1m 26s
Cost:
$0.006756
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
"You're trembling. Tell me you haven't eaten the gluten-free lemon tart yet." "I haven't. I found something wedged under the display case. Miller's deed to the old gristmill." "Miller's been dust for a decade. Who's claiming the land?" "That's the problem. The flour sack near the door was slashed, leaking like a heartbeat, and someone wrote 'Stop' in red icing on the window." "Red icing? That's raspberry glaze, from the batch we made before the power outage." "Exactly. Someone was here before opening. And they knew which batch we'd check." The bell above the door jingles. They both freeze, eyes darting to the shadows near the register. "Well, grab the baguette. It's heavy enough to crack a skull and perfect for a stakeout." "Just keep your voice down. Sheriff Higgins is eyeing the muffin tin like it owes him money." "He suspects everyone. But if he finds that deed, the festival is dead in the water." The flour dust hangs thick in the air, smelling of almonds and trouble. A scribbled scrap floats down from the sourdough crock. "The festival is already in trouble. Someone left a note in the starter. 'Digging graves pays better.'" "Then pass me the knife. We'd better check who's hiding in the walk-in cooler."
created_at
"2026-04-27T08:12:52.002Z"
4/27/2026, 8:12:52 AM
model
"qwen/qwen3.5-plus-20260420"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
653
moderation_latency
(null)
generation_time
42650
tokens_prompt
81
tokens_completion
2867
native_tokens_prompt
78
native_tokens_completion
2802
native_tokens_completion_images
(null)
native_tokens_reasoning
2502
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
num_fetches
(null)
web_search_engine
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.006756
router
(null)
provider_responses
0
endpoint_id
"8b4a0fbb-6705-4f8d-a7f1-ad18ecc0edbc"
id
"chatcmpl-2a228aac-7e84-935f-9578-f8449c75c131"
is_byok
false
latency
653
model_permaslug
"qwen/qwen3.5-plus-20260420"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777277572-gZZgHGqpYaN3rjZLtwQi"
session_id
(null)
api_type
"completions"
id
"gen-1777277572-WXZEr40Y5MOE8kqx2zRS"
upstream_id
"chatcmpl-2a228aac-7e84-935f-9578-f8449c75c131"
total_cost
0.006756
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)