NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-03-11-01KKFHR6BHXCJKZ8BTYYX2P3KJ
Run Details
Model:
Qwen 3.5 9B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
2m 12s
Cost:
$0.001358
Provider:
Together
Evaluation summary
Score
Evaluator
Details Link
99.92%
Matches word count
(details)
36.79%
Dialogue to Total Word Ratio
(details)
68.3535%
Overall
Model input
User/Human
You are a author of comedic heist books. Please write a 200 word scene that has 10% words of dialogue between two thieves named Molly and Bill who are planning to break into a children's party to steal all the presents. Only include the prose of the scene without any markdown or commentary.
Model response
Messages
Meta
AI
The massive white elephant spread its legs across the living room, flapping silent wings against shimmering lights. Molly adjusted her disguise, loosening her grandmother's lacy collar while inspecting the perimeter through binoculars. The scent of cinnamon and sugary frosting overpowered the natural fear of the room. Beside her, Bill adjusted his trilby hat. A child wandered too close, waving a plastic sword toward the adults. Molly froze, clutching her clipboard like a holy book. She watched the parents flip through birthday invitations while the children monitored the plates. Bill checked his watch, tapping the glass nervously. The disco music played a slow waltz over the misty eyes of the guests. Molly scanned the floorboards. She looked for the shadow under the table. The floorboards were thin wood under her boots. Bill grinned and touched his hat. He held a knife. The knife was sharp. Is it secure? Bill whispered. Door is weak. We go. Gifts belong to us. We do not come back. Let's go. They stood there. The shadow moved closer to the window quickly. Parents sat quietly. The music stopped suddenly. A siren beeped loudly in the air. They ran away from the house past the gate. The rain started falling.
created_at
"2026-03-11T22:54:46.654Z"
3/11/2026, 10:54:46 PM
model
"qwen/qwen3.5-9b-20260310"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
271
moderation_latency
(null)
generation_time
131877
tokens_prompt
77
tokens_completion
7942
native_tokens_prompt
76
native_tokens_completion
9001
native_tokens_completion_images
(null)
native_tokens_reasoning
7631
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
0.00135775
router
(null)
provider_responses
0
endpoint_id
"00d506d9-a5e9-4382-a2b9-d54732365594"
id
"oagmf6b-3pDw3Z-9dae2495b1266c3f"
is_byok
false
latency
271
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-1773269686-jiiNtjSty9stAMDe5xd1"
upstream_id
"oagmf6b-3pDw3Z-9dae2495b1266c3f"
total_cost
0.00135775
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Together"
Evaluation details
Result
Evaluator
Details
Meta Data
99.92%
Matches word count
n/a
neededClean
false
words
203
36.79%
Dialogue to Total Word Ratio
Ratio: 0.00%, Deviation: 10.00%
neededClean
false
wordsTotal
203
wordsDialogue
0
68.3535%