NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-02-25-01KJBGH5C2EB3TCQJP3NH14TEA
Run Details
Model:
Qwen 3.5 122B
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 15s
Cost:
$0.037992
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
43.38%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
71.6873%
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
Molly adjusted her tactical goggles, scanning the suburban backyard through the van’s rearview mirror. The inflatable bouncy castle loomed like a pink fortress guarding the loot. Bill counted the stack of wrapped boxes beneath the oak tree, his fingers trembling. The smell of sugar and sweat filled the humid air. “Thirty units,” Bill whispered. Molly nodded solemnly. “The parents will be distracted by the piñata.” She checked her watch. The clown arrived at four. They had twenty minutes. Bill pulled out a grappling hook, but Molly slapped his hand away. “No noise,” she hissed. “We’re ghosts.” Bill grinned, adjusting his mask. “Like Batman.” “No Batman,” Molly warned. “We’re pros.” They crept toward the fence, stepping over garden gnomes with military precision. A balloon popped inside, echoing like a gunshot. Both froze. A toddler laughed, oblivious to the danger lurking in the shadows. Molly signaled forward. Bill loaded the sack with practiced ease. This wasn’t just theft; it was a rescue mission for the toys trapped in plastic. The risk was high, but the potential payout was legendary. They moved like shadows, leaving no trace except a few missing crayons. The parents would never know their kids were sad. Molly checked the thermal scope one last time. Everything was clear. The wind howled softly around the dark house.
created_at
"2026-02-25T23:00:48.136Z"
2/25/2026, 11:00:48 PM
model
"qwen/qwen3.5-122b-a10b-20260224"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
388
moderation_latency
(null)
generation_time
75414
tokens_prompt
77
tokens_completion
10907
native_tokens_prompt
76
native_tokens_completion
11863
native_tokens_completion_images
(null)
native_tokens_reasoning
11568
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
0.037992
router
(null)
provider_responses
0
endpoint_id
"33d466d1-d2f7-45ed-8ff3-fda7d2e32351"
id
"chatcmpl-9d5788a0-54ba-9087-8518-bce3afdb2733"
is_byok
false
latency
388
model_permaslug
"qwen/qwen3.5-122b-a10b-20260224"
provider_name
"Alibaba"
status
200
api_type
"completions"
id
"gen-1772060448-btqrteBBedsbc7rhlVPB"
upstream_id
"chatcmpl-9d5788a0-54ba-9087-8518-bce3afdb2733"
total_cost
0.037992
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
Evaluation details
Result
Evaluator
Details
Meta Data
43.38%
Matches word count
n/a
neededClean
false
words
217
100.00%
Dialogue to Total Word Ratio
Ratio: 9.22%, Deviation: 0.78%
neededClean
false
wordsTotal
217
wordsDialogue
20
71.6873%