NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1KZ9GWEH3XGZBQJ5EP4KSQF
Run Details
Model:
Qwen 3.8 27B (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
1m 52s
Cost:
$0.018281
Provider:
Cloudflare
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
"Butter scones, and not one without a crack?" The morning bell above the door jingled in the small-town bakery. Flour dust swirled in a pale beam of sunlight, and brown butter filled the room. "Cracks are how bread breathes." "They're how secrets leak, too." A tray of cinnamon rolls cooled on the counter, their edges glistening. In the back, a mixer hummed, then died. "Town isn't ready for secrets this close to the river festival." "Nor is it for a bakery without them. The mayor's wife ordered a cherry cake this morning. Three layers, vanilla filling, no frosting." "An odd request for a funeral." "Only if someone died." "Harold Finch died." "The town already decided that. A dead man in the river, a missing locket, and a bakery that smells of yeast and trouble." The door jingled again. A newspaper lay damp on the floor, and a cake tin rattled on the shelf. "She called. She wants the cherry cake canceled." "Then we'll bake a plum tart instead. Tarts are less likely to be tampered with." "Less likely?" "Someone can't slice a tart into three layers." The morning bell jingled once more, soft as a guilty secret, and the oven ticked.
created_at
"2026-09-03T15:48:09.239Z"
9/3/2026, 3:48:09 PM
model
"qwen/qwen3.8-27b-20260814"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
353
moderation_latency
(null)
generation_time
112319
tokens_prompt
78
tokens_completion
4469
native_tokens_prompt
120
native_tokens_completion
5696
native_tokens_completion_images
(null)
native_tokens_reasoning
4170
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"
service_tier
(null)
usage
0.0182812
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788450489-3B4begMSs9HElMWTUtt9"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788450489-pLMd7gnna1zQYFFc610t"
upstream_id
"id-1788450489440"
provider_responses
0
endpoint_id
"e56a0de7-f040-4dee-a36a-824fb379d883"
id
"id-1788450489440"
is_byok
false
latency
205
model_permaslug
"qwen/qwen3.8-27b-20260814"
provider_name
"Cloudflare"
status
200
total_cost
0.0182812
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Cloudflare"
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)