NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M0V6B06865JYX9Y6608QNA
Run Details
Model:
Qwen 3.8 27B (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
2m 18s
Cost:
$0.013936
Provider:
Reka
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 bakery’s oven ticked, cinnamon filling the air. “Did you see the new delivery note?” “It was under the cash register. Flour smudges on the corner.” “The owner isn’t back until Thursday.” “Which means someone opened the back door after closing.” A tray of cardamom knots cooled on the counter, their sugar shells cracking with the slightest touch. “I counted the boxes. Twelve, not ten.” “And the extra box?” “Empty now. But the straw was fresh, and a black ribbon had been tied around it.” The bell above the door jingled, though no one entered. “Maybe it was a gift.” “Gifts don’t arrive at two in the morning.” A small paper receipt lay beneath the display case, its ink still damp. “Who bought a loaf of bread at two in the morning?” The lights dimmed, then returned. On the flour-dusted tile, a single footprint pointed toward the walk-in freezer. A soft click came from inside. “The freezer’s locked from the inside.” “But the light is off.” A radio crackled once, then fell silent. In the window, the street glowed. Far away, a car door closed. The old bakery smelled of warm bread, butter, sugar, and unanswered questions for now.
created_at
"2026-09-03T16:15:16.84Z"
9/3/2026, 4:15:16 PM
model
"qwen/qwen3.8-27b-20260814"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
220
moderation_latency
(null)
generation_time
138173
tokens_prompt
78
tokens_completion
4478
native_tokens_prompt
120
native_tokens_completion
5454
native_tokens_completion_images
(null)
native_tokens_reasoning
4155
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
0.0139365
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788452116-FihGscrqPQrUvC8BaFdZ"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788452116-2T6oSxo8emqWDldmzPev"
upstream_id
"chatcmpl-7f8107b7-0615-4f0c-89f6-5817c08020bd"
provider_responses
0
endpoint_id
"15086968-df2f-4d69-86bb-c74c31644bb6"
id
"chatcmpl-7f8107b7-0615-4f0c-89f6-5817c08020bd"
is_byok
false
latency
220
model_permaslug
"qwen/qwen3.8-27b-20260814"
provider_name
"Reka"
status
200
total_cost
0.0139365
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Reka"
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)