NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-03-01M1M052SSV9YAAZ2GFY50B5SK
Run Details
Model:
Qwen 3.8 27B (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
1m 26s
Cost:
$0.010025
Provider:
Reka
Evaluation summary
Score
Evaluator
Details Link
0.00%
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 sourdough cooled in the window case, its crust crackling with every tick of the oven timer. Vanilla and caramel drifted over the marble counter, but the register drawer gaped a few dollars short. A copper bell above the door had been jiggled too hard, leaving a faint scratch on the paint. Someone set a napkin beside the cash box, then folded its corner with suspicious care. You didn’t bake the lemon loaves yesterday. No one baked them. The delivery van didn’t arrive before six. The health inspector came by before closing. His shoes were muddy. Muddy? The sidewalk had been dry since breakfast, and the rain ended two days ago. Then who put the note in the proofing cabinet? It was warm when I found it, tucked beneath the butter croissants. The cabinet? That’s impossible. The bread room was locked, and I threw the new key away. Not impossible. Just inconvenient. Mrs. Bellamy asked for the recipe card again. I told her I’d send it by morning. She looked at the window while she smiled. Looking at a window is not a confession. No. But a new lock on the back door, and a flour handprint on the inside handle, is.
created_at
"2026-09-03T16:03:12.326Z"
9/3/2026, 4:03:12 PM
model
"qwen/qwen3.8-27b-20260814"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
232
moderation_latency
(null)
generation_time
86391
tokens_prompt
78
tokens_completion
3174
native_tokens_prompt
120
native_tokens_completion
3920
native_tokens_completion_images
(null)
native_tokens_reasoning
2882
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
0.0100248
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788451392-tXxnPbKsOH8GajObhF3v"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788451392-TsWsh49vDyLlNuGKVZ1s"
upstream_id
"chatcmpl-421d81fd-bcdb-4469-aa55-498ddfcf8806"
provider_responses
0
endpoint_id
"15086968-df2f-4d69-86bb-c74c31644bb6"
id
"chatcmpl-421d81fd-bcdb-4469-aa55-498ddfcf8806"
is_byok
false
latency
232
model_permaslug
"qwen/qwen3.8-27b-20260814"
provider_name
"Reka"
status
200
total_cost
0.0100248
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
0.00%
Count dialogue tags
n/a
neededClean
false
noDialogue
true