NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-04-27-01KQ74GF1C950WMSB4WTFC5PAZ
Run Details
Model:
Qwen 3.6 35B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
31.9s
Cost:
$0.005022
Provider:
AtlasCloud
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 oven timer dinged. Dust motes danced in afternoon light on the flour-dusted tables. Burnt sugar masked the metallic tang of fear. "You're humming again. That means you're nervous, or you've just solved a murder." "It means the sourdough is perfect. Unlike some people who leave muddy boots on the evidence counter." "These aren't boots. And it wasn't evidence. It was a warning." A bell jingled. A customer entered. Neither baker looked up. One kneaded rhythmically, the other scrubbed the counter with aggressive circles. "Mrs. Higgins wants the scones. She mentioned you were arguing with the vicar near the crypt." "We weren't arguing. We were debating theology. And the location of the missing parish funds." "The vicar turned pale when you mentioned the safe. You must have slipped up." "I slipped nothing. I simply mentioned I'd found a receipt in the confessional. A receipt for a very expensive necklace, signed in a hand I recognized." "Oh, dear. Did you say whose hand?" "That's why I'm kneading. So the dough doesn't hear me whisper it." "Well, whisper faster. The vicar is heading this way, and he's wearing that red velvet sash."
created_at
"2026-04-27T09:32:13.748Z"
4/27/2026, 9:32:13 AM
model
"qwen/qwen3.6-35b-a3b-20260415"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1015
moderation_latency
(null)
generation_time
31697
tokens_prompt
81
tokens_completion
4573
native_tokens_prompt
78
native_tokens_completion
5190
native_tokens_completion_images
(null)
native_tokens_reasoning
4916
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
0.005022221
router
(null)
provider_responses
0
endpoint_id
"179c6985-3a1c-48f1-a009-9f3e3e402cdd"
id
"cbb01030e1b9473b8a8eb24a5517f812"
is_byok
false
latency
1015
model_permaslug
"qwen/qwen3.6-35b-a3b-20260415"
provider_name
"AtlasCloud"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.1; linux; x64))"
http_referer
(null)
request_id
"req-1777282333-u5hlXHyUyJ71kOknl44I"
session_id
(null)
api_type
"completions"
id
"gen-1777282333-BZAQaDC1eoRjn3DBKs4S"
upstream_id
"cbb01030e1b9473b8a8eb24a5517f812"
total_cost
0.005022221
cache_discount
(null)
upstream_inference_cost
0
provider_name
"AtlasCloud"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)