NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2026-09-02-01M1HAX595C3Z7B3R8P5J260WS
Run Details
Model:
Qwen 3.8 Max (Reasoning, XHigh)
Test:
Dialogue tags
Scenario:
Write 200 words with 10% dialogue
Duration:
1m 45s
Cost:
$0.027530
Provider:
Alibaba
Evaluation summary
Score
Evaluator
Details Link
100.00%
Matches word count
(details)
100.00%
Dialogue to Total Word Ratio
(details)
100.0000%
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
They had spent three weeks studying the birthday fortress: a bouncy castle, a piƱata lookout, and six sticky toddlers patrolling the gift table. Molly had forged a glittery vendor badge, while Bill had memorized the exact squeak of the party gate. Their plan relied on a vanilla distraction, a puppet emergency, and a wagon with suspiciously deep compartments. Outside, balloons bobbed like tiny informants. Inside, wrapped loot waited beneath a tablecloth printed with cartoon sharks. Molly checked her candy-cam. Bill adjusted his suspenders, which were absolutely not filled with backup wrapping paper. The doorbell chimed. Somewhere a child screamed for pizza. The heist clock began ticking. Molly spread the crayon blueprint across the van floor. "We enter as magicians, not clowns." Bill polished a tiny wand. "I hate rabbits." Molly tucked a stolen invitation beside a frosting gun. "Then bring cake, not balloons." Bill frowned at his pocket watch. "Cake is heavier." Molly winked. "Deliciously heavier." Bill nodded. "Right." Molly raised three gloved fingers, then two, then one, because dramatic countdowns were cheap and free. Bill swallowed. The gate squeaked exactly as predicted. Children gasped. A magician entered. A cake followed. Presents trembled. The birthday loot was doomed almost immediately.
created_at
"2026-09-02T15:13:24.033Z"
9/2/2026, 3:13:24 PM
model
"qwen/qwen3.8-max-20260803"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
1680
moderation_latency
(null)
generation_time
104879
tokens_prompt
75
tokens_completion
3829
native_tokens_prompt
127
native_tokens_completion
4546
native_tokens_completion_images
(null)
native_tokens_reasoning
4253
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
0.02753
router
(null)
user_agent
"langchainjs-openai/1.0.0 ((node/v24.19.0; linux; x64))"
http_referer
(null)
request_id
"req-1788362004-9eo6NSKvqMRVGyKRg5U3"
session_id
(null)
preset_id
(null)
api_type
"completions"
id
"gen-1788362004-IZOH6A7LCPvo1QUUsIqt"
upstream_id
"chatcmpl-87faf426-80f1-967d-8e6c-9f58f2566029"
provider_responses
0
endpoint_id
"6332e9fd-e0c4-4cae-8c17-d25bc774864a"
id
"chatcmpl-87faf426-80f1-967d-8e6c-9f58f2566029"
is_byok
false
latency
1680
model_permaslug
"qwen/qwen3.8-max-20260803"
provider_name
"Alibaba"
status
200
total_cost
0.02753
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Alibaba"
response_cache_source_id
(null)
data_region
"global"
workspace_id
"97e315e5-d303-487d-83c1-83180e8a13d4"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Matches word count
n/a
neededClean
false
words
200
100.00%
Dialogue to Total Word Ratio
Ratio: 9.95%, Deviation: 0.05%
neededClean
false
wordsTotal
201
wordsDialogue
20
100.0000%