NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-11-11-01M75NJAZZAHAH81XGH2FZAK5G
Run Details
Model:
Hy4 (Reasoning, High)
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
1m 23s
Cost:
$0.010680
Provider:
Tencent
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 door bell cheeped, and Main Street fog slipped into the bakery. Cinnamon steam softened the windows; currant scones cooled by the register. A card advertised raspberry tarts for the Harvest Social. "Someone moved the ledger." "Moved it, or borrowed it to recount the cinnamon vote?" "Borrowed things return before the icing sets. This was left instead." Lavender stationery lay under the string, floury but for one purple smear. "Blackcurrant jam. Nobody in Little Mallow uses it in September." "Nobody who admits it. Did you hear the back window rattle?" "At six, with the clock striking and the delivery boy whistling off-key. A crumb waited on the sill." "Shortcrust, with caraway." "Exactly like the biscuits entered last year by the jam judge." "He died before the ribbons were announced." "The coroner called it natural causes. But his recipe card vanished, and now Blackcurrant Surprise is on Saturday's list." "Then we bake a batch." "For the social?" "For bait. Whoever steals one will need a napkin, a guilty conscience, and that ledger." "Leave the door unbolted?" "No. Leave cinnamon dust on the counter. Small-town clues tread softly." "And if the thief is a friend?" "Then we pour tea before asking questions."
created_at
"2026-11-11T16:03:01.259Z"
11/11/2026, 4:03:01 PM
model
"tencent/hy4-20261104"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1057
moderation_latency
(null)
generation_time
82998
tokens_prompt
78
tokens_completion
8473
native_tokens_prompt
83
native_tokens_completion
8513
native_tokens_completion_images
(null)
native_tokens_reasoning
8217
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
0.010680117
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.22.2; linux; x64))"
http_referer
(null)
request_id
"req-1794412981-kAvBtSE1OMX8huTBp5ZW"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1794412981-ev4ltUNbA96gjFIL4LGp"
upstream_id
"38f12b7c-43db-43e1-87de-2dc74e022595"
provider_responses
0
endpoint_id
"b5b076de-19fd-4e5c-adc2-2420a425969e"
id
"38f12b7c-43db-43e1-87de-2dc74e022595"
is_byok
false
latency
1057
model_permaslug
"tencent/hy4-20261104"
provider_name
"Tencent"
status
200
total_cost
0.010680117
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Tencent"
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)