NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-05-22-01KS87DVVNCXE4PQWMXDH8Z1XV
Run Details
Model:
Qwen3.7 Max
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
1m 16s
Cost:
$0.038347
Provider:
Alibaba
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 scent of toasted pecans and melted butter hung heavy in the crisp morning air. Fine white flour dusted the scarred butcher block island like a fresh, undisturbed snowfall. "Did you check the false bottom of the flour tin?" "I checked everywhere. Even inside the bubbling sourdough starter." A silver pastry scraper rhythmically chopped through a block of cold butter, the sharp metal clicking against the wood. "It has to be here. Mayor Higgins didn't just vanish into thin air after eating that lemon tart." "Maybe he didn't vanish. Maybe someone helped him disappear before the sun came up." The rhythmic scraping abruptly stopped. A fine mist of flour settled over a tiny, tarnished brass key resting on the wooden board. "Is that..." "Found it baked right into the crust of his leftovers." "But the bakery doors were deadbolted all night." "Exactly. Which means our killer has a spare key, a hidden agenda, and a serious sweet tooth." "Should we call the sheriff?" "Not yet. First, we need to find out what this opens before the morning rush arrives and washes away our only clue." The oven timer chimed, signaling the cinnamon rolls were finally done.
created_at
"2026-05-22T16:13:52.387Z"
5/22/2026, 4:13:52 PM
model
"qwen/qwen3.7-max-20260520"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
871
moderation_latency
(null)
generation_time
76284
tokens_prompt
81
tokens_completion
3736
native_tokens_prompt
78
native_tokens_completion
5087
native_tokens_completion_images
(null)
native_tokens_reasoning
4821
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
0.0383475
router
(null)
provider_responses
0
endpoint_id
"6d30fdc6-f2a7-4bdf-b6ba-32353496d723"
id
"chatcmpl-39bf4843-2fe2-90f4-8962-ad294d0eee25"
is_byok
false
latency
871
model_permaslug
"qwen/qwen3.7-max-20260520"
provider_name
"Alibaba"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.15.0; linux; x64))"
http_referer
(null)
request_id
"req-1779466432-vTkJ0AJTtfKxBIzvfs1x"
session_id
(null)
api_type
"completions"
id
"gen-1779466432-xFtQ0hUlF0WxQ8wV0Wbf"
upstream_id
"chatcmpl-39bf4843-2fe2-90f4-8962-ad294d0eee25"
total_cost
0.0383475
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)