NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M1MMZRFVNABT02Q6V1RSWW
Run Details
Model:
Qwen 3.8 27B (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
2m 19s
Cost:
$0.025535
Provider:
Phala
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
Morning light fell on the counter where cardamom buns steamed in a glass case. The bell above the door chimed. “One for the regular?” “Only if there’s coffee left.” “The good kind, not the sludge from the urn?” “Of course. You have taste.” “The almond croissant?” “Take two. They won’t last until noon.” “Someone always saves the last one for the mayor.” “Let him learn the taste of defeat.” Outside, the square was empty except for the ice-cream truck’s slow notes. Inside, the oven ticked. “That’s what I like about this town. Everything is fresh until it isn’t.” “And the gossip is stale by afternoon.” “Stale? No. It’s proof. It tells you what people have been chewing on all week.” A paper bag rustled. “Two croissants, one bun, black coffee?” “Perfect.” The register clinked. “Wrap it in the blue paper?” “The blue. With the little flour hearts.” “Those were your grandmother’s.” “Then make it official. Every visit feels like a reunion.” The door opened, releasing a draft that made the cinnamon sticks on the display shift. A child outside pressed a nose to the window, tracing a heart in the condensation. The bell chimed once more, patient as a secret.
created_at
"2026-09-03T16:29:11.039Z"
9/3/2026, 4:29:11 PM
model
"qwen/qwen3.8-27b-20260814"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
378
moderation_latency
(null)
generation_time
138640
tokens_prompt
78
tokens_completion
6368
native_tokens_prompt
188
native_tokens_completion
8494
native_tokens_completion_images
(null)
native_tokens_reasoning
8193
native_tokens_cached
64
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"
service_tier
(null)
usage
0.0255348
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788452951-AeWqq35xv34aE5fq6Cyo"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788452951-EhBzCGzCM02QNlLflPSc"
upstream_id
"req_cf453ede1ece558d0397d33ab116065f"
provider_responses
0
endpoint_id
"cfc4d0ca-df7c-4b5f-9c74-328c41a7cbc3"
id
"req_cf453ede1ece558d0397d33ab116065f"
is_byok
false
latency
377
model_permaslug
"qwen/qwen3.8-27b-20260814"
provider_name
"Phala"
status
200
total_cost
0.0255348
cache_discount
0.0000224
upstream_inference_cost
0
provider_name
"Phala"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)