NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFGR9H3GGJC050DQKRWZT5S
Run Details
Model:
Qwen 3.5 9B
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
1m 25s
Cost:
$0.001467
Provider:
Together
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
Flour dusted the moonlight through the high windows, settling gently over the cooling proofers. Dust danced in the warm air. The scent of apple pie baking filled the space, competing with old wood and sweet tea. "You think the man in black dropped the evidence in the bin again?" Silence filled the room for a beat. "Or maybe Taylor just finally confessed to stealing the antique rolling pin." "The pin doesn’t have fingerprints." "But the new tourist does." They moved closer to the heat, breath visible against the blinds. Outside, the car idled, then stopped. "The bin door doesn’t latch." "How did the cat get in there if the handle was broken?" "It wasn’t the cat." A spoon tapped amber glass. "I saw your neighbor, Perkins, peeking through the front window at ten last night. He was too quiet." "Perkins hates cats." "Say goodbye to the rolling pin today." "Tell him the oatmeal cookies are poisoned." "Careful. He’s the one who runs the hardware store." "He also owns the boat in the river." "And I hate perfect scones." The bell chimed above the door. "One phone call." Steam rose from the oven.
created_at
"2026-03-11T22:37:21.329Z"
3/11/2026, 10:37:21 PM
model
"qwen/qwen3.5-9b-20260310"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
364
moderation_latency
(null)
generation_time
84575
tokens_prompt
81
tokens_completion
8830
native_tokens_prompt
78
native_tokens_completion
9730
native_tokens_completion_images
(null)
native_tokens_reasoning
8519
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"stop"
usage
0.0014673
router
(null)
provider_responses
0
endpoint_id
"00d506d9-a5e9-4382-a2b9-d54732365594"
id
"oaggJN8-3pDw3Z-9dae0b1096256c69"
is_byok
false
latency
364
model_permaslug
"qwen/qwen3.5-9b-20260310"
provider_name
"Together"
status
200
user_agent
"langchainjs-openai/1.0.0 ((node/v24.14.0; linux; x64))"
http_referer
(null)
api_type
"completions"
id
"gen-1773268641-iu7Byl6Ic0Epdqj33Mgx"
upstream_id
"oaggJN8-3pDw3Z-9dae0b1096256c69"
total_cost
0.0014673
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)